Daily Papers

Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents this, as current interfaces lack real-time verbalization and robust user barge-in. We present AsyncVoice Agent, a system whose asynchronous architecture decouples a streaming LLM backend from a conversational voice frontend. This design allows narration and inference to run in parallel, empowering users to interrupt, query, and steer the model's reasoning process at any time. Objective benchmarks show this approach reduces interaction latency by more than 600x compared to monolithic baselines while ensuring high fidelity and competitive task accuracy. By enabling a two-way dialogue with a model's thought process, AsyncVoice Agent offers a new paradigm for building more effective, steerable, and trustworthy human-AI systems for high-stakes tasks.

Multimodal Large Language Models excel at offline audio-visual understanding, but their ability to serve as mobile assistants in continuous real-world streams remains underexplored. In daily phone use, mobile assistants must track streaming audio-visual inputs and respond at the right time, yet existing benchmarks are often restricted to multiple-choice questions or use shorter videos. In this paper, we introduce PhoStream, the first mobile-centric streaming benchmark that unifies on-screen and off-screen scenarios to evaluate video, audio, and temporal reasoning. PhoStream contains 5,572 open-ended QA pairs from 578 videos across 4 scenarios and 10 capabilities. We build it with an Automated Generative Pipeline backed by rigorous human verification, and evaluate models using a realistic Online Inference Pipeline and LLM-as-a-Judge evaluation for open-ended responses. Experiments reveal a temporal asymmetry in LLM-judged scores (0-100): models perform well on Instant and Backward tasks (Gemini 3 Pro exceeds 80), but drop sharply on Forward tasks (16.40), largely due to early responses before the required visual and audio cues appear. This highlights a fundamental limitation: current MLLMs struggle to decide when to speak, not just what to say. Code and datasets used in this work will be made publicly accessible at https://github.com/Lucky-Lance/PhoStream.

To render each generated token in real-time for users, the Large Language Model (LLM) server generates tokens one by one and streams each token (or group of a few tokens) through the network to the user right after generation, which we refer to as LLM token streaming. However, under unstable network conditions, the LLM token streaming experience could suffer greatly from stalls since one packet loss could block the rendering of later tokens even if the packets containing them arrive on time. With a measurement study, we show that current applications suffer from increased stalls under unstable networks. For this emerging token streaming problem in LLM Chatbots that differs from previous multimedia and text applications, we propose a novel transmission scheme, called Eloquent, which puts newly generated tokens as well as currently unacknowledged tokens in the next outgoing packet. This ensures that each packet contains some new tokens and, in the meantime, is independently rendered when received, avoiding the aforementioned stalls caused by missing packets. Through simulation under various networks, we show Eloquent reduces stall ratio (proportion of token rendering wait time) by 71.0% compared to the retransmission method commonly used by real chatbot applications and by 31.6% compared to the baseline packet duplication scheme. By tailoring Eloquent to fit the token-by-token generation of LLM, we enable the Chatbots to respond like an eloquent speaker for users to better enjoy pervasive AI.

Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous tokens' Key and Value states (KV) consumes extensive memory. Secondly, popular LLMs cannot generalize to longer texts than the training sequence length. Window attention, where only the most recent KVs are cached, is a natural approach -- but we show that it fails when the text length surpasses the cache size. We observe an interesting phenomenon, namely attention sink, that keeping the KV of initial tokens will largely recover the performance of window attention. In this paper, we first demonstrate that the emergence of attention sink is due to the strong attention scores towards initial tokens as a ``sink'' even if they are not semantically important. Based on the above analysis, we introduce StreamingLLM, an efficient framework that enables LLMs trained with a finite length attention window to generalize to infinite sequence lengths without any fine-tuning. We show that StreamingLLM can enable Llama-2, MPT, Falcon, and Pythia to perform stable and efficient language modeling with up to 4 million tokens and more. In addition, we discover that adding a placeholder token as a dedicated attention sink during pre-training can further improve streaming deployment. In streaming settings, StreamingLLM outperforms the sliding window recomputation baseline by up to 22.2x speedup. Code and datasets are provided at https://github.com/mit-han-lab/streaming-llm.

We present OnPrem.LLM, a Python-based toolkit for applying large language models (LLMs) to sensitive, non-public data in offline or restricted environments. The system is designed for privacy-preserving use cases and provides prebuilt pipelines for document processing and storage, retrieval-augmented generation (RAG), information extraction, summarization, classification, and prompt/output processing with minimal configuration. OnPrem.LLM supports multiple LLM backends -- including llama.cpp, Ollama, vLLM, and Hugging Face Transformers -- with quantized model support, GPU acceleration, and seamless backend switching. Although designed for fully local execution, OnPrem.LLM also supports integration with a wide range of cloud LLM providers when permitted, enabling hybrid deployments that balance performance with data control. A no-code web interface extends accessibility to non-technical users.

The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilitates partial tool execution. Our results demonstrate that tool partial execution can improve request completion latency by up to 38.8%.

Recent works have shown that large language model (LLM) agents are able to improve themselves from experience, which is an important ability for continuous enhancement post-deployment. However, existing benchmarks primarily evaluate their innate capabilities and do not assess their ability to improve over time. To address this gap, we introduce StreamBench, a pioneering benchmark designed to evaluate the continuous improvement of LLM agents over an input-feedback sequence. StreamBench simulates an online learning environment where LLMs receive a continuous flow of feedback stream and iteratively enhance their performance. In addition, we propose several simple yet effective baselines for improving LLMs on StreamBench, and provide a comprehensive analysis to identify critical components that contribute to successful streaming strategies. Our work serves as a stepping stone towards developing effective online learning strategies for LLMs, paving the way for more adaptive AI systems in streaming scenarios.

Large Language Models (LLMs) are primarily designed for batch processing. Existing methods for adapting LLMs to streaming rely either on expensive re-encoding or specialized architectures with limited scalability. This work identifies three key mismatches in adapting batch-oriented LLMs to streaming: (1) input-attention, (2) output-attention, and (3) position-ID mismatches. While it is commonly assumed that the latter two mismatches require frequent re-encoding, our analysis reveals that only the input-attention mismatch significantly impacts performance, indicating re-encoding outputs is largely unnecessary. To better understand this discrepancy with the common assumption, we provide the first comprehensive analysis of the impact of position encoding on LLMs in streaming, showing that preserving relative positions within source and target contexts is more critical than maintaining absolute order. Motivated by the above analysis, we introduce a group position encoding paradigm built on batch architectures to enhance consistency between streaming and batch modes. Extensive experiments on cross-lingual and cross-modal tasks demonstrate that our method outperforms existing approaches. Our method requires no architectural modifications, exhibits strong generalization in both streaming and batch modes. The code is available at repository https://github.com/EIT-NLP/StreamingLLM.

Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented reality. However, these models face fundamental memory and computational challenges because their key-value (KV) caches grow substantially with continuous streaming video input. This process requires an iterative prefill stage, which is a unique feature of streaming video LLMs. Due to its iterative prefill stage, it suffers from significant limitations, including extensive computation, substantial data transfer, and degradation in accuracy. Crucially, this issue is exacerbated for edge deployment, which is the primary target for these models. In this work, we propose V-Rex, the first software-hardware co-designed accelerator that comprehensively addresses both algorithmic and hardware bottlenecks in streaming video LLM inference. At its core, V-Rex introduces ReSV, a training-free dynamic KV cache retrieval algorithm. ReSV exploits temporal and spatial similarity-based token clustering to reduce excessive KV cache memory across video frames. To fully realize these algorithmic benefits, V-Rex offers a compact, low-latency hardware accelerator with a dynamic KV cache retrieval engine (DRE), featuring bit-level and early-exit based computing units. V-Rex achieves unprecedented real-time of 3.9-8.3 FPS and energy-efficient streaming video LLM inference on edge deployment with negligible accuracy loss. While DRE only accounts for 2.2% power and 2.0% area, the system delivers 1.9-19.7x speedup and 3.1-18.5x energy efficiency improvements over AGX Orin GPU. This work is the first to comprehensively tackle KV cache retrieval across algorithms and hardware, enabling real-time streaming video LLM inference on resource-constrained edge devices.

The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating tool calling across multiple LLM providers remains a core engineering challenge due to fragmented APIs, incompatible message formats, and inconsistent streaming and tool-calling behavior, making it difficult to build portable, reliable agent systems. We introduce Orchestral, a lightweight Python framework that provides a unified, type-safe interface for building LLM agents across major providers while preserving the simplicity required for scientific computing and production deployment. Orchestral defines a single universal representation for messages, tools, and LLM usage that operates seamlessly across providers, eliminating manual format translation and reducing framework-induced complexity. Automatic tool schema generation from Python type hints removes the need for handwritten descriptors while maintaining type safety across provider boundaries. A synchronous execution model with streaming support enables deterministic behavior, straightforward debugging, and real-time interaction without introducing server dependencies. The framework's modular architecture cleanly separates provider integration, tool execution, conversation orchestration, and user-facing interfaces, enabling extensibility without architectural entanglement. Orchestral supports advanced agent capabilities found in larger frameworks, including rich tool calling, context compaction, workspace sandboxing, user approval workflows, sub-agents, memory management, and MCP integration.

The advent of large language models (LLMs) has transformed text-based services, enabling capabilities ranging from real-time translation to AI-driven chatbots. However, existing serving systems primarily focus on optimizing server-side aggregate metrics like token generation throughput, ignoring individual user experience with streamed text. As a result, under high and/or bursty load, a significant number of users can receive unfavorable service quality or poor Quality-of-Experience (QoE). In this paper, we first formally define QoE of text streaming services, where text is delivered incrementally and interactively to users, by considering the end-to-end token delivery process throughout the entire interaction with the user. Thereafter, we propose Andes, a QoE-aware serving system that enhances user experience for LLM-enabled text streaming services. At its core, Andes strategically allocates contended GPU resources among multiple requests over time to optimize their QoE. Our evaluations demonstrate that, compared to the state-of-the-art LLM serving systems like vLLM, Andes improves the average QoE by up to 3.2times under high request rate, or alternatively, it attains up to 1.6times higher request rate while preserving high QoE.

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality). Streaming context incrementally--overlapping retrieval with inference--can mitigate this latency, but doing so with concurrent requests introduces new challenges: requests contend for GPU compute and memory, and scheduling must adapt to dynamic context arrivals. We present Stream2LLM, a streaming-aware LLM serving system for concurrent prefill-decode disaggregated deployments. Stream2LLM introduces adaptive scheduling and preemption for two distinct retrieval patterns: append-mode (progressive context accumulation) and update-mode (iterative refinement with cache invalidation). It decouples scheduling decisions from resource acquisition, enabling flexible preemption strategies guided by hardware-specific cost models, and uses longest common prefix matching to minimize redundant computation when input changes dynamically. To evaluate Stream2LLM, we collect two large-scale, real-world streaming workloads based on web crawling and approximate nearest neighbor search. Our evaluation demonstrates that streaming architecture delivers up to 11x TTFT improvements, with cost-aware scheduling providing critical benefits under memory pressure, all while maintaining throughput parity with non-streaming baselines. Code: https://github.com/rajveerb/stream2llm/tree/mlsys_artifact

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.

Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat videos as predetermined clips, making them less effective and efficient at handling streaming video inputs. In this paper, we propose a novel Learning-In-Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training objective designed to perform language modeling for continuous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming dialogue format, and (3) an optimized inference pipeline to speed up the model responses in real-world video streams. With our LIVE framework, we built VideoLLM-online model upon Llama-2/Llama-3 and demonstrate its significant advantages in processing streaming videos. For instance, on average, our model can support streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. Moreover, it also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at https://showlab.github.io/videollm-online.

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive requests emphasizing per-token latency in streaming chat, deadline-sensitive requests requiring rapid full responses to trigger external tools, and compound requests with evolving dependencies across multiple LLM calls. Despite-or perhaps, because of-this workload diversity and unpredictable request information (e.g., response lengths and dependencies), existing request schedulers have focused on aggregate performance, unable to ensure application-level SLO needs. This paper presents JITServe, the first SLO-aware LLM serving system designed to maximize service goodput (e.g., the number of tokens meeting request SLOs) across diverse workloads. JITServe novelly schedules requests using imprecise request information and gradually relaxes this conservatism by refining request information estimates as generation progresses. It applies a grouped margin goodput maximization algorithm to allocate just enough serving bandwidth to satisfy each request's SLO just-in-time (JIT), maximizing residual capacity for others, while deciding the composition of requests in a batch to maximize efficiency and goodput with provable guarantees. Our evaluation across diverse realistic workloads, including chat, deep research, and agentic pipelines, shows that JITServe improves service goodput by 1.4x-6.3x, alternatively achieving 28.5%-83.2% resource savings, compared to state-of-the-art designs.

We present StreamBridge, a simple yet effective framework that seamlessly transforms offline Video-LLMs into streaming-capable models. It addresses two fundamental challenges in adapting existing models into online scenarios: (1) limited capability for multi-turn real-time understanding, and (2) lack of proactive response mechanisms. Specifically, StreamBridge incorporates (1) a memory buffer combined with a round-decayed compression strategy, supporting long-context multi-turn interactions, and (2) a decoupled, lightweight activation model that can be effortlessly integrated into existing Video-LLMs, enabling continuous proactive responses. To further support StreamBridge, we construct Stream-IT, a large-scale dataset tailored for streaming video understanding, featuring interleaved video-text sequences and diverse instruction formats. Extensive experiments show that StreamBridge significantly improves the streaming understanding capabilities of offline Video-LLMs across various tasks, outperforming even proprietary models such as GPT-4o and Gemini 1.5 Pro. Simultaneously, it achieves competitive or superior performance on standard video understanding benchmarks.

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

The exploration and application of Large Language Models (LLMs) is thriving. To reduce deployment costs, continuous batching has become an essential feature in current service frameworks. The effectiveness of continuous batching relies on an accurate estimate of the memory requirements of requests. However, due to the diversity in request output lengths, existing frameworks tend to adopt aggressive or conservative schedulers, which often result in significant overestimation or underestimation of memory consumption. Consequently, they suffer from harmful request evictions or prolonged queuing times, failing to achieve satisfactory throughput under strict Service Level Agreement (SLA) guarantees (a.k.a. goodput), across various LLM application scenarios with differing input-output length distributions. To address this issue, we propose a novel Past-Future scheduler that precisely estimates the peak memory resources required by the running batch via considering the historical distribution of request output lengths and calculating memory occupancy at each future time point. It adapts to applications with all types of input-output length distributions, balancing the trade-off between request queuing and harmful evictions, thereby consistently achieving better goodput. Furthermore, to validate the effectiveness of the proposed scheduler, we developed a high-performance LLM serving framework, LightLLM, that implements the Past-Future scheduler. Compared to existing aggressive or conservative schedulers, LightLLM demonstrates superior goodput, achieving up to 2-3times higher goodput than other schedulers under heavy loads. LightLLM is open source to boost the research in such direction (https://github.com/ModelTC/lightllm).

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must be processed online, and questions need timely responses. In this work, we propose a training-free approach compatible with standard Video-LLMs, leveraging three key concepts: 1) LLM-informed selection of visual tokens to identify those that the LLM has attended to and contributed to its understanding of each short clip. Our attention-based selection allows us to discard up to ~95% of unimportant visual tokens with minimal performance loss; 2) Recurrent processing of past selected tokens to generate temporally coherent understanding of each processed clip; 3) Caption-based question answering for lightweight and accurate responses. Our method achieves state-of-the-art performance on streaming video benchmarks, striking a balance between efficiency and effectiveness.

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs, which scale LLM calls and output tokens to help AI agents reason, explore, and solve complex tasks. However, existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization. Our analysis reveals that programs submitted to LLM serving engines experience long cumulative wait times, primarily due to head-of-line blocking at both the individual LLM request and the program. To address this, we introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies. Autellix intercepts LLM calls submitted by programs, enriching schedulers with program-level context. We propose two scheduling algorithms-for single-threaded and distributed programs-that preempt and prioritize LLM calls based on their programs' previously completed calls. Our evaluation demonstrates that across diverse LLMs and agentic workloads, Autellix improves throughput of programs by 4-15x at the same latency compared to state-of-the-art systems, such as vLLM.

Many networking tasks now employ deep learning (DL) to solve complex prediction and system optimization problems. However, current design philosophy of DL-based algorithms entails intensive engineering overhead due to the manual design of deep neural networks (DNNs) for different networking tasks. Besides, DNNs tend to achieve poor generalization performance on unseen data distributions/environments. Motivated by the recent success of large language models (LLMs), for the first time, this work studies the LLM adaptation for networking to explore a more sustainable design philosophy. With the massive pre-trained knowledge and powerful inference ability, LLM can serve as the foundation model, and is expected to achieve "one model for all" with even better performance and stronger generalization for various tasks. In this paper, we present NetLLM, the first LLM adaptation framework that efficiently adapts LLMs to solve networking problems. NetLLM addresses many practical challenges in LLM adaptation, from how to process task-specific information with LLMs, to how to improve the efficiency of answer generation and acquiring domain knowledge for networking. Across three networking-related use cases - viewport prediction (VP), adaptive bitrate streaming (ABR) and cluster job scheduling (CJS), we showcase the effectiveness of NetLLM in LLM adaptation for networking. Results show that the adapted LLM surpasses state-of-the-art algorithms by 10.1-36.6% for VP, 14.5-36.6% for ABR, 6.8-41.3% for CJS, and also achieves superior generalization performance.

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demand low job completion time (JCT) for model inference. Existing LLM serving systems use run-to-completion processing for inference jobs, which suffers from head-of-line blocking and long JCT. We present FastServe, a distributed inference serving system for LLMs. FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. FastServe uses preemptive scheduling to minimize JCT with a novel skip-join Multi-Level Feedback Queue scheduler. Based on the new semi information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join. The higher priority queues than the joined queue are skipped to reduce demotions. We design an efficient GPU memory management mechanism that proactively offloads and uploads intermediate states between GPU memory and host memory for LLM inference. We build a system prototype of FastServe based on NVIDIA FasterTransformer. Experimental results show that compared to the state-of-the-art solution Orca, FastServe improves the average and tail JCT by up to 5.1times and 6.4times, respectively.

Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentary, and embodied robots. An ideal streaming system should support proactive interaction, long-horizon memory, and real-time processing, while resting on a VLM backbone capable of handling diverse in-the-wild streaming tasks. However, existing VLMs excel at offline video understanding but fall short in streaming capabilities and lack dedicated infrastructure for streaming deployment. We address this gap on three fronts. (i) For backbone capability, we construct Streaming-Train-248K, a streaming dataset paired with a novel training objective for adapting VLMs to streaming interaction and understanding. (ii) For real-world deployment, we introduce Streaming Harness, a plug-and-play system that endows any VLM with three core abilities: proactive interaction (per-second response decisions), long-term memory (12-hour context retention), and real-time processing (sub-second latency). (iii) To drive continued community progress on streaming capabilities, we design Streaming-Eval, a benchmark that reflects models' capabilities across diverse in-the-wild scenarios. Extensive experiments demonstrate consistent gains from our approach across all core capabilities required for streaming video understanding. We will open-source our data, code, and benchmark to advance the community's shift from offline video understanding to deployable streaming intelligence.

As Large Language Models (LLMs) are rapidly growing in popularity, LLM inference services must be able to serve requests from thousands of users while satisfying performance requirements. The performance of an LLM inference service is largely determined by the hardware onto which it is deployed, but understanding of which hardware will deliver on performance requirements remains challenging. In this work we present LLM-Pilot - a first-of-its-kind system for characterizing and predicting performance of LLM inference services. LLM-Pilot performs benchmarking of LLM inference services, under a realistic workload, across a variety of GPUs, and optimizes the service configuration for each considered GPU to maximize performance. Finally, using this characterization data, LLM-Pilot learns a predictive model, which can be used to recommend the most cost-effective hardware for a previously unseen LLM. Compared to existing methods, LLM-Pilot can deliver on performance requirements 33% more frequently, whilst reducing costs by 60% on average.

The wide adoption of LLMs has led to their use in great variety of applications and scenarios, such as chatbot assistants and data annotation, creating the need for the models to satisfy certain budget and hardware constraints. This has led to the trend of LLMs being released in batches consisting of similar models of various sizes for the family of models to adhere to as wide of a range of constraints as possible. In this paper, we validate distillation and quantization as a cost-effective way to expand model families to new sizes and hardware formats. Based on the open-recipe Apertus 8B LLM, we produce Apertus-v1.1 - a distilled family of models with up to 4B parameters trained on 1.7T permissive license tokens. We demonstrate cost-efficiency and strong accuracy performance of our approach for covering large ranges of hardware and systems requirements.

Serial LLM inference backends -- such as Ollama -- process requests one at a time under FCFS admission, causing Head-of-Line Blocking (HOLB) under mixed workloads at high utilisation: short factual queries can be delayed by minutes behind long generation jobs. While cloud-scale deployments mitigate HOLB via continuous batching (vLLM, Orca), these solutions require tens of GB of VRAM for concurrent KV-caches -- infeasible for memory-constrained edge and local deployments that rely on serial request dispatch. We present \clairvoyant, a drop-in sidecar proxy for any serial OpenAI-compatible backend (e.g., Ollama, llama.cpp). \clairvoyant predicts response length from 19 lightweight lexical features via an ONNX-exported XGBoost classifier, achieving 0.029\,ms per-request latency (four orders of magnitude below typical generation time). Because admission scheduling depends on relative ordering rather than exact prediction, the system optimises ranking fidelity, achieving 62--96\% in-distribution and 52--66\% cross-distribution accuracy across natural conversation datasets. We find that curated instruction datasets are degenerate training sources for length prediction: GPT-imposed brevity constraints reduce Long-class representation to under 0.02\% of examples, making natural conversation logs the only viable training source. End-to-end GPU benchmarks on an RTX~4090 show 70--76\% P50 latency reduction for short requests under maximum queue pressure (100 concurrent requests) and 17\% under steady-state Poisson arrivals (ρ=0.74). \clairvoyant is open-source and requires no modifications to the inference backend.

Many applications must provide low-latency LLM service to users or risk unacceptable user experience. However, over-provisioning resources to serve fluctuating request patterns is often prohibitively expensive. In this work, we present a best-effort serving system that employs deep reinforcement learning to adjust service quality based on the task distribution and system load. Our best-effort system can maintain availability with over 10x higher client request rates, serves above 96% of peak performance 4.1x more often, and serves above 98% of peak performance 2.3x more often than static serving on unpredictable workloads. Our learned router is robust to shifts in both the arrival and task distribution. Compared to static serving, learned best-effort serving allows for cost-efficient serving through increased hardware utility. Additionally, we argue that learned best-effort LLM serving is applicable in wide variety of settings and provides application developers great flexibility to meet their specific needs.

The rapid proliferation of Large Language Models (LLMs) has been a driving force in the growth of cloud-based LLM services, which are now integral to advancing AI applications. However, the dynamic auto-regressive nature of LLM service, along with the need to support exceptionally long context lengths, demands the flexible allocation and release of substantial resources. This presents considerable challenges in designing cloud-based LLM service systems, where inefficient management can lead to performance degradation or resource wastage. In response to these challenges, this work introduces DistAttention, a novel distributed attention algorithm that segments the KV Cache into smaller, manageable units, enabling distributed processing and storage of the attention module. Based on that, we propose DistKV-LLM, a distributed LLM serving system that dynamically manages KV Cache and effectively orchestrates all accessible GPU and CPU memories spanning across the data center. This ensures a high-performance LLM service on the cloud, adaptable to a broad range of context lengths. Validated in a cloud environment with 32 NVIDIA A100 GPUs in configurations from 2 to 32 instances, our system exhibited 1.03-2.4x end-to-end throughput improvements and supported context lengths 2-19x longer than current state-of-the-art LLM service systems, as evidenced by extensive testing across 18 datasets with context lengths up to 1,900K.

With the rise of real-world human-AI interaction applications, such as AI assistants, the need for Streaming Video Dialogue is critical. To address this need, we introduce StreamMind, a video LLM framework that achieves ultra-FPS streaming video processing (100 fps on a single A100) and enables proactive, always-on responses in real time, without explicit user intervention. To solve the key challenge of the contradiction between linear video streaming speed and quadratic transformer computation cost, we propose a novel perception-cognition interleaving paradigm named ''event-gated LLM invocation'', in contrast to the existing per-time-step LLM invocation. By introducing a Cognition Gate network between the video encoder and the LLM, LLM is only invoked when relevant events occur. To realize the event feature extraction with constant cost, we propose Event-Preserving Feature Extractor (EPFE) based on state-space method, generating a single perception token for spatiotemporal features. These techniques enable the video LLM with full-FPS perception and real-time cognition response. Experiments on Ego4D and SoccerNet streaming tasks, as well as standard offline benchmarks, demonstrate state-of-the-art performance in both model capability and real-time efficiency, paving the way for ultra-high-FPS applications, such as Game AI and interactive media. The code and data is available at https://aka.ms/StreamMind.

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of processing dense visual tokens from continuous video streams. In streaming video scenarios, the primary bottleneck lies in the Vision Transformer (ViT) encoding stage, where redundant processing of temporally similar frames leads to inefficiency. Additionally, inflated token sequences during LLM pre-filling further exacerbate latency and memory overhead. To address these challenges, we propose Streaming Token Compression (STC), a plug-and-play hierarchical framework that seamlessly integrates into existing streaming VideoLLMs, optimizing both ViT encoding and LLM pre-filling stages to accelerate processing. STC introduces two token-level accelerators: STC-Cacher, which reduces ViT encoding overhead by caching and reusing features from temporally similar frames, and STC-Pruner, which compresses the visual token sequence before it enters the LLM, preserving only the most salient tokens based on both spatial and temporal relevance. Extensive experiments on four baseline streaming VideoLLMs across five benchmarks demonstrate that STC outperforms other compression methods. Notably, STC retains up to 99\% of accuracy on the ReKV framework while reducing ViT encoding latency and LLM pre-filling latency by 24.5\% and 45.3\%.

The rise of large language models (LLMs) has enabled LLM-based applications (a.k.a. AI agents or co-pilots), a new software paradigm that combines the strength of LLM and conventional software. Diverse LLM applications from different tenants could design complex workflows using multiple LLM requests to accomplish one task. However, they have to use the over-simplified request-level API provided by today's public LLM services, losing essential application-level information. Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM applications. This paper introduces Parrot, an LLM service system that focuses on the end-to-end experience of LLM-based applications. Parrot proposes Semantic Variable, a unified abstraction to expose application-level knowledge to public LLM services. A Semantic Variable annotates an input/output variable in the prompt of a request, and creates the data pipeline when connecting multiple LLM requests, providing a natural way to program LLM applications. Exposing Semantic Variables to the public LLM service allows it to perform conventional data flow analysis to uncover the correlation across multiple LLM requests. This correlation opens a brand-new optimization space for the end-to-end performance of LLM-based applications. Extensive evaluations demonstrate that Parrot can achieve up to an order-of-magnitude improvement for popular and practical use cases of LLM applications.

We present a systematic, empirical evaluation of five local large language model (LLM) runtimes on Apple Silicon: MLX, MLC-LLM, llama.cpp, Ollama, and PyTorch MPS. Experiments were conducted on a Mac Studio equipped with an M2 Ultra processor and 192 GB of unified memory. Using the Qwen-2.5 model family across prompts ranging from a few hundred to 100,000 tokens, we measure time-to-first-token (TTFT), steady-state throughput, latency percentiles, long-context behavior (key-value and prompt caching), quantization support, streaming performance, batching and concurrency behavior, and deployment complexity. Under our settings, MLX achieves the highest sustained generation throughput, while MLC-LLM delivers consistently lower TTFT for moderate prompt sizes and offers stronger out-of-the-box inference features. llama.cpp is highly efficient for lightweight single-stream use, Ollama emphasizes developer ergonomics but lags in throughput and TTFT, and PyTorch MPS remains limited by memory constraints on large models and long contexts. All frameworks execute fully on-device with no telemetry, ensuring strong privacy guarantees. We release scripts, logs, and plots to reproduce all results. Our analysis clarifies the design trade-offs in Apple-centric LLM deployments and provides evidence-based recommendations for interactive and long-context processing. Although Apple Silicon inference frameworks still trail NVIDIA GPU-based systems such as vLLM in absolute performance, they are rapidly maturing into viable, production-grade solutions for private, on-device LLM inference.

LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms. Traditional approaches rely on procedural JSON-based function calling, which often struggles with long-horizon tasks due to fragile multi-turn dependencies and context drift. In this paper, we present CaveAgent, a framework that transforms the paradigm from "LLM-as-Text-Generator" to "LLM-as-Runtime-Operator." We introduce a Dual-stream Context Architecture that decouples state management into a lightweight semantic stream for reasoning and a persistent, deterministic Python Runtime stream for execution. In addition to leveraging code generation to efficiently resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, we introduce Stateful Runtime Management in CaveAgent. Distinct from existing code-based approaches that remain text-bound and lack the support for external object injection and retrieval, CaveAgent injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns. This persistence mechanism acts as a high-fidelity external memory to eliminate context drift, avoid catastrophic forgetting, while ensuring that processed data flows losslessly to downstream applications. Comprehensive evaluations on Tau^2-bench, BFCL and various case studies across representative SOTA LLMs demonstrate CaveAgent's superiority. Specifically, our framework achieves a 10.5\% success rate improvement on retail tasks and reduces total token consumption by 28.4\% in multi-turn scenarios. On data-intensive tasks, direct variable storage and retrieval reduces token consumption by 59\%, allowing CaveAgent to handle large-scale data that causes context overflow failures in both JSON-based and Code-based agents.

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and service quality. In this paper, we reexamine this assumption -- we show that, although predicting the exact generation length of each request is infeasible, it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. The ranking information offers valuable guidance for scheduling requests. Building on this insight, we develop a novel scheduler for LLM inference and serving that can approximate the shortest-job-first (SJF) schedule better than existing approaches. We integrate this scheduler with the state-of-the-art LLM serving system and show significant performance improvement in several important applications: 2.8x lower latency in chatbot serving and 6.5x higher throughput in synthetic data generation. Our code is available at https://github.com/hao-ai-lab/vllm-ltr.git

It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each stage (e.g., speech denoising, speech enhancement, speaker diarization, and punctuation models), which themselves demand high-quality training data and are rarely open-sourced. Even with state-of-the-art models, issues persist, such as incomplete background noise removal and misalignment between punctuation and actual speech pauses. Moreover, the stringent filtering strategies often retain only 10-30\% of the original data, significantly impeding data scaling efforts. In this work, we leverage a noise-robust audio tokenizer (S3Tokenizer) to design a simplified yet effective TTS data processing pipeline that maintains data quality while substantially reducing data acquisition costs, achieving a data retention rate of over 50\%. Beyond data scaling challenges, LLM-based TTS systems also incur higher deployment costs compared to conventional approaches. Current systems typically use LLMs solely for text-to-token generation, while requiring separate models (e.g., flow matching models) for token-to-waveform generation, which cannot be directly executed by LLM inference engines, further complicating deployment. To address these challenges, we eliminate redundant modules in both LLM and flow components, replacing the flow model backbone with an LLM architecture. Building upon this simplified flow backbone, we propose a unified architecture for both streaming and non-streaming inference, significantly reducing deployment costs. Finally, we explore the feasibility of unifying TTS and ASR tasks using the same data for training, thanks to the simplified pipeline and the S3Tokenizer that reduces the quality requirements for TTS training data.

Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to-SQL systems in production poses substantial challenges due to their inherently multi-stage workflows, stringent latency constraints, and potentially heterogeneous GPU infrastructure in enterprise environments. Current LLM serving frameworks lack effective mechanisms for handling interdependent inference tasks, dynamic latency variability, and resource heterogeneity, leading to suboptimal performance and frequent service-level objective (SLO) violations. In this paper, we introduce HEXGEN-TEXT2SQL, a novel framework designed explicitly to schedule and execute agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters that handle multi-tenant end-to-end queries. HEXGEN-TEXT2SQL introduce a hierarchical scheduling approach combining global workload-balanced task dispatching and local adaptive urgency-guided prioritization, guided by a systematic analysis of agentic Text-to-SQL workflows. Additionally, we propose a lightweight simulation-based method for tuning critical scheduling hyperparameters, further enhancing robustness and adaptability. Our extensive evaluation on realistic Text-to-SQL benchmarks demonstrates that HEXGEN-TEXT2SQL significantly outperforms state-of-the-art LLM serving frameworks. Specifically, HEXGEN-TEXT2SQL reduces latency deadlines by up to 1.67times (average: 1.41times) and improves system throughput by up to 1.75times (average: 1.65times) compared to vLLM under diverse, realistic workload conditions. Our code is available at https://github.com/Relaxed-System-Lab/Hexgen-Flow.

We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answering or captioning, Streamo performs a broad spectrum of streaming video tasks, including real-time narration, action understanding, event captioning, temporal event grounding, and time-sensitive question answering. To develop such versatility, we construct Streamo-Instruct-465K, a large-scale instruction-following dataset tailored for streaming video understanding. The dataset covers diverse temporal contexts and multi-task supervision, enabling unified training across heterogeneous streaming tasks. After training end-to-end on the instruction-following dataset through a streamlined pipeline, Streamo exhibits strong temporal reasoning, responsive interaction, and broad generalization across a variety of streaming benchmarks. Extensive experiments show that Streamo bridges the gap between offline video perception models and real-time multimodal assistants, making a step toward unified, intelligent video understanding in continuous video streams.

We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best latency for voice agents, fully self-hosted end-to-end solutions are not yet available. We evaluate the closest candidate, Qwen3-Omni, across three configurations: its cloud-only DashScope Realtime API achieves sim702ms audio-to-audio latency with streaming, but is not self-hostable; its local vLLM deployment supports only the Thinker (text generation from audio, 516ms), not the Talker (audio synthesis); and its local Transformers deployment runs the full pipeline but at sim146s -- far too slow for realtime. The cascaded streaming pipeline (STT rightarrow LLM rightarrow TTS) therefore remains the practical architecture for self-hosted realtime voice agents, and the focus of this tutorial. We build a complete voice agent using Deepgram (streaming STT), vLLM-served LLMs with function calling (streaming text generation), and ElevenLabs (streaming TTS), achieving a measured time-to-first-audio of 755ms (best case 729ms) with full function calling support. We release the full codebase as a 9-chapter progressive tutorial with working, tested code for every component.

Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long video sequences, supporting multi-turn dialogues, and adapting to real-world dynamic scenarios. To address these issues, we propose StreamChat, a training-free framework for streaming video reasoning and conversational interaction. StreamChat leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequences, enabling real-time, multi-turn dialogue. Our framework incorporates a parallel system scheduling strategy that enhances processing speed and reduces latency, ensuring robust performance in real-world applications. Furthermore, we introduce StreamBench, a versatile benchmark that evaluates streaming video understanding across diverse media types and interactive scenarios, including multi-turn interactions and complex reasoning tasks. Extensive evaluations on StreamBench and other public benchmarks demonstrate that StreamChat significantly outperforms existing state-of-the-art models in terms of accuracy and response times, confirming its effectiveness for streaming video understanding. Code is available at StreamChat: https://github.com/hmxiong/StreamChat.

Large Language Models (LLMs) have achieved remarkable success in serving end-users with human-like intelligence. However, LLMs demand high computational resources, making it challenging to deploy them to satisfy various performance objectives, such as meeting the resource constraints on edge devices close to end-users or achieving high accuracy with ample resources. In this paper, we introduce CE-CoLLM, a novel cloud-edge collaboration framework that supports efficient and adaptive LLM inference for end-users at the edge with two modes, (1) low-latency edge standalone inference and (2) highly accurate cloud-edge collaborative inference. First, we show that the inherent high communication costs for transmitting LLM contextual information between the edge and cloud dominate the overall latency, making it inefficient and costly to deploy LLMs using cloud-edge collaboration. Second, we propose several critical techniques to address this challenge, including early-exit mechanism, cloud context manager, and quantization in cloud-edge collaboration to enable not only low-latency standalone edge inference but also efficient and adaptive cloud-edge collaborative inference for LLMs. Third, we perform comprehensive experimental analysis, which demonstrates that CE-CoLLM significantly reduces inference time by up to 13.81% and cloud computation costs by up to 84.55% compared to the popular cloud-based LLM deployment, while maintaining comparable model accuracy. The proposed approach effectively shifts the computational load to the edge, reduces the communication overhead, scales efficiently with multiple edge clients, and provides reliable LLM deployment using cloud-edge collaboration.

The widespread adoption of cloud-based proprietary large language models (LLMs) has introduced significant challenges, including operational dependencies, privacy concerns, and the necessity of continuous internet connectivity. In this work, we introduce an LLMOps pipeline, "LlamaDuo", for the seamless migration of knowledge and abilities from service-oriented LLMs to smaller, locally manageable models. This pipeline is crucial for ensuring service continuity in the presence of operational failures, strict privacy policies, or offline requirements. Our LlamaDuo involves fine-tuning a small language model against the service LLM using a synthetic dataset generated by the latter. If the performance of the fine-tuned model falls short of expectations, it is enhanced by further fine-tuning with additional similar data created by the service LLM. This iterative process guarantees that the smaller model can eventually match or even surpass the service LLM's capabilities in specific downstream tasks, offering a practical and scalable solution for managing AI deployments in constrained environments. Extensive experiments with leading edge LLMs are conducted to demonstrate the effectiveness, adaptability, and affordability of LlamaDuo across various downstream tasks. Our pipeline implementation is available at https://github.com/deep-diver/llamaduo.

Large Language Models (LLMs) are increasingly applied to data-intensive workflows, from database querying to developer observability. Yet the effectiveness of these systems is constrained by the volume, verbosity, and noise of real-world text-rich data such as logs, telemetry, and monitoring streams. Feeding such data directly into LLMs is costly, environmentally unsustainable, and often misaligned with task objectives. Parallel efforts in LLM efficiency have focused on model- or architecture-level optimizations, but the challenge of reducing upstream input verbosity remains underexplored. In this paper, we argue for treating the token budget of an LLM as an attention budget and elevating task-aware text reduction as a first-class design principle for language -- data systems. We position input-side reduction not as compression, but as attention allocation: prioritizing information most relevant to downstream tasks. We outline open research challenges for building benchmarks, designing adaptive reduction pipelines, and integrating token-budget--aware preprocessing into database and retrieval systems. Our vision is to channel scarce attention resources toward meaningful signals in noisy, data-intensive workflows, enabling scalable, accurate, and sustainable LLM--data integration.

Video Large Language Models (VideoLLMs) have achieved strong performance on many video understanding tasks, but most existing systems remain offline and are not well-suited for live video streams that require continuous observation and timely response. Recent streaming VideoLLMs have made progress, yet current approaches often rely on decoupled trigger-response pipelines or are limited to captioning-style narration, reducing their effectiveness for open-ended question answering and long-horizon interaction. We propose AURA (Always-On Understanding and Real-Time Assistance), an end-to-end streaming visual interaction framework that enables a unified VideoLLM to continuously process video streams and support both real-time question answering and proactive responses. AURA integrates context management, data construction, training objectives, and deployment optimization for stable long-horizon streaming interaction. It achieves state-of-the-art performance on streaming benchmarks and supports a real-time demo system with ASR and TTS running at 2 FPS on two 80G accelerators. We release the AURA model together with a real-time inference framework to facilitate future research.

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL frameworks face challenges in complex dataflows and the corresponding resource idling and workload imbalance. Moreover, most existing frameworks are tightly coupled with LLM training or inference engines, making it difficult to support custom-designed engines. To address these challenges, we propose AsyncFlow, an asynchronous streaming RL framework for efficient post-training. Specifically, we introduce a distributed data storage and transfer module that provides a unified data management and fine-grained scheduling capability in a fully streamed manner. This architecture inherently facilitates automated pipeline overlapping among RL tasks and dynamic load balancing. Moreover, we propose a producer-consumer-based asynchronous workflow engineered to minimize computational idleness by strategically deferring parameter update process within staleness thresholds. Finally, the core capability of AsynFlow is architecturally decoupled from underlying training and inference engines and encapsulated by service-oriented user interfaces, offering a modular and customizable user experience. Extensive experiments demonstrate an average of 1.59 throughput improvement compared with state-of-the-art baseline. The presented architecture in this work provides actionable insights for next-generation RL training system designs.

Large language models (LLMs) have revolutionized natural language processing with their exceptional capabilities. However, deploying LLMs on resource-constrained edge devices presents significant challenges due to computational limitations, memory constraints, and edge hardware heterogeneity. This survey summarizes recent developments in edge LLMs across their lifecycle, examining resource-efficient designs from pre-deployment techniques to runtime optimizations. Additionally, it explores on-device LLM applications in personal, enterprise, and industrial scenarios. By synthesizing advancements and identifying future directions, this survey aims to provide a comprehensive understanding of state-of-the-art methods for deploying LLMs on edge devices, bridging the gap between their immense potential and edge computing limitations.

Leveraging the rapid development of Large Language Models LLMs, LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and security of LLM-based agents during applications. However, the safety issues of LLM-based agents are currently under-explored. In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents. We first formulate a general framework of agent backdoor attacks, then we present a thorough analysis on the different forms of agent backdoor attacks. Specifically, from the perspective of the final attacking outcomes, the attacker can either choose to manipulate the final output distribution, or only introduce malicious behavior in the intermediate reasoning process, while keeping the final output correct. Furthermore, the former category can be divided into two subcategories based on trigger locations: the backdoor trigger can be hidden either in the user query or in an intermediate observation returned by the external environment. We propose the corresponding data poisoning mechanisms to implement the above variations of agent backdoor attacks on two typical agent tasks, web shopping and tool utilization. Extensive experiments show that LLM-based agents suffer severely from backdoor attacks, indicating an urgent need for further research on the development of defenses against backdoor attacks on LLM-based agents. Warning: This paper may contain biased content.

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient in scale and scope, thus failing to fully capture intricate workload characteristics. In this paper, we fill the gap with an in-depth characterization of LLM serving workloads collected from our worldwide cloud inference serving service, covering not only language models but also emerging multimodal and reasoning models, and unveiling important new findings in each case. Moreover, based on our findings, we propose ServeGen, a principled framework for generating realistic LLM serving workloads by composing them on a per-client basis. A practical use case in production validates that ServeGen avoids 50% under-provisioning compared to naive workload generation, demonstrating ServeGen's advantage in performance benchmarking. We will open-source ServeGen to foster future research.

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times. In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.

Many LLM tasks are performed in large batches or even offline, and the performance indictor for which is throughput. These tasks usually show the characteristic of prefix sharing, where different prompt input can partially show the common prefix. However, the existing LLM inference engines tend to optimize the streaming requests and show limitations of supporting the large batched tasks with the prefix sharing characteristic. The existing solutions use the LRU-based cache to reuse the KV context of common prefix. The KV context that is about to be reused may prematurely be evicted with the implicit cache management. Even if not evicted, the lifetime of the shared KV context is extended since requests sharing the same context are not scheduled together, resulting in larger memory usage. These streaming oriented systems schedule the requests in the first-come-first-serve or similar order. As a result, the requests with larger ratio of decoding steps may be scheduled too late to be able to mix with the prefill chunks to increase the hardware utilization. Besides, the token and request number based batching can limit the size of token-batch, which keeps the GPU from saturating for the iterations dominated by decoding tokens. We propose BatchLLM to address the above problems. BatchLLM explicitly identifies the common prefixes globally. The requests sharing the same prefix will be scheduled together to reuse the KV context the best, which also shrinks the lifetime of common KV memory. BatchLLM reorders the requests and schedules the requests with larger ratio of decoding first to better mix the decoding tokens with the latter prefill chunks and applies memory-centric token batching to enlarge the token-batch sizes, which helps to increase the GPU utilization. Extensive evaluation shows that BatchLLM outperforms vLLM by 1.1x to 2x on a set of microbenchmarks and two typical industry workloads.

Deploying large language models (LLMs) on mobile devices is an emerging trend to enable data privacy and offline accessibility of LLM applications. Modern mobile neural processing units (NPUs) make such deployment increasingly feasible. However, existing mobile LLM inference frameworks suffer from high start-up latency due to their inevitable cold starts, i.e., launching LLM inferences when the model is not hosted in device memory. In this paper, we identify the key bottleneck of mobile LLM cold starts as the waste of flash bandwidth on unimportant model parameters. We design EdgeFlow, a mobile LLM inference framework that mitigates the cold start issue by adaptively adjusting the precisions of LLM parameters. Specifically, EdgeFlow leverages 1) an NPU-aware adaptive quantization algorithm that assigns different precisions to weights in a finer granularity according to their importance and NPU constraints, 2) an SIMD-friendly packing format that accelerates the transformation of various-precision weights into fixed-sized NPU-native data types, and 3) a synergistic granular pipeline that coordinates CPU and NPU computation in a fine-grained and dynamic manner. Experimental results show that EdgeFlow reduces cold-start latency by up to 4.07x compared with three state-of-the-art mobile LLM inference frameworks, i.e., llama.cpp, MNN, and llm.npu, under comparable model accuracy.

Large language models (LLMs) are useful in many NLP tasks and become more capable with size, with the best open-source models having over 50 billion parameters. However, using these 50B+ models requires high-end hardware, making them inaccessible to most researchers. In this work, we investigate methods for cost-efficient inference and fine-tuning of LLMs, comparing local and distributed strategies. We observe that a large enough model (50B+) can run efficiently even on geodistributed devices in a consumer-grade network. This could allow running LLM efficiently by pooling together idle compute resources of multiple research groups and volunteers. We address two open problems: (1) how to perform inference and fine-tuning reliably if any device can disconnect abruptly and (2) how to partition LLMs between devices with uneven hardware, joining and leaving at will. In order to do that, we develop special fault-tolerant inference algorithms and load-balancing protocols that automatically assign devices to maximize the total system throughput. We showcase these algorithms in Petals - a decentralized system that runs Llama 2 (70B) and BLOOM (176B) over the Internet up to 10x faster than offloading for interactive generation. We evaluate the performance of our system in simulated conditions and a real-world setup spanning two continents.

Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs, aiming to select the best-performing LLMs tailored to the domains of user queries, while managing computational resources. However, current routing approaches often face limitations in scalability when dealing with a large pool of specialized LLMs, or in their adaptability to extending model scope and evolving capability domains. To overcome those challenges, we propose InferenceDynamics, a flexible and scalable multi-dimensional routing framework by modeling the capability and knowledge of models. We operate it on our comprehensive dataset RouteMix, and demonstrate its effectiveness and generalizability in group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench, showcasing its ability to identify and leverage top-performing models for given tasks, leading to superior outcomes with efficient resource utilization. The broader adoption of Inference Dynamics can empower users to harness the full specialized potential of the LLM ecosystem, and our code will be made publicly available to encourage further research.

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving. By leveraging these technologies, we demonstrate how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios. Through real-world evaluations using Kubernetes-based autoscaling, we show that Cloud Native architectures can dynamically adapt to workload fluctuations, mitigating performance bottlenecks while optimizing LLM inference serving performance. This discussion provides a broader perspective on how Cloud Native frameworks could reshape the future of scalable LLM inference serving, offering key insights for researchers, practitioners, and industry leaders in cloud computing and artificial intelligence.

The rapid growth of online video platforms, particularly live streaming services, has created an urgent need for real-time video understanding systems. These systems must process continuous video streams and respond to user queries instantaneously, presenting unique challenges for current Video Large Language Models (VideoLLMs). While existing VideoLLMs excel at processing complete videos, they face significant limitations in streaming scenarios due to their inability to handle dense, redundant frames efficiently. We introduce TimeChat-Online, a novel online VideoLLM that revolutionizes real-time video interaction. At its core lies our innovative Differential Token Drop (DTD) module, which addresses the fundamental challenge of visual redundancy in streaming videos. Drawing inspiration from human visual perception's Change Blindness phenomenon, DTD preserves meaningful temporal changes while filtering out static, redundant content between frames. Remarkably, our experiments demonstrate that DTD achieves an 82.8% reduction in video tokens while maintaining 98% performance on StreamingBench, revealing that over 80% of visual content in streaming videos is naturally redundant without requiring language guidance. To enable seamless real-time interaction, we present TimeChat-Online-139K, a comprehensive streaming video dataset featuring diverse interaction patterns including backward-tracing, current-perception, and future-responding scenarios. TimeChat-Online's unique Proactive Response capability, naturally achieved through continuous monitoring of video scene transitions via DTD, sets it apart from conventional approaches. Our extensive evaluation demonstrates TimeChat-Online's superior performance on streaming benchmarks (StreamingBench and OvOBench) and maintaining competitive results on long-form video tasks such as Video-MME and MLVU.

Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and increasingly powerful consumer devices have made on-device deployment practical. The web browser as a platform for on-device deployment is universally accessible, provides a natural agentic environment, and conveniently abstracts out the different backends from diverse device vendors. To address this opportunity, we introduce WebLLM, an open-source JavaScript framework that enables high-performance LLM inference entirely within web browsers. WebLLM provides an OpenAI-style API for seamless integration into web applications, and leverages WebGPU for efficient local GPU acceleration and WebAssembly for performant CPU computation. With machine learning compilers MLC-LLM and Apache TVM, WebLLM leverages optimized WebGPU kernels, overcoming the absence of performant WebGPU kernel libraries. Evaluations show that WebLLM can retain up to 80% native performance on the same device, with room to further close the gap. WebLLM paves the way for universally accessible, privacy-preserving, personalized, and locally powered LLM applications in web browsers. The code is available at: https://github.com/mlc-ai/web-llm.

Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a percentage point. At the same time, the computational cost of evaluating modern LLMs has driven widespread adoption of specialized inference backends, software systems that execute trained models efficiently at inference time. While critical for scalability, system-level optimizations, such as custom CUDA kernels and reduced-precision arithmetic, can alter token probabilities and introduce non-determinism, possibly cascading into divergent generation. In this work, we first survey the inference landscape, identifying 200 distinct engines, and analyze 35,000 ML publications, finding that the specific inference stack is rarely reported despite this widespread diversity. We then present a systematic empirical study of how inference backends affect LLM benchmark results. Holding model weights, decoding parameters, and hardware constant, we evaluate five widely used inference engines, including vLLM, SGLang, and llama.cpp, across multiple open-weight models and established benchmarks. We show that the choice of backend alone can shift benchmark scores by up to 16.6 percentage points and induce high rates of output disagreement. By isolating backend optimizations and tracing the execution pipeline, we find this divergence is driven by system-level optimizations like prefix caching and CUDA graphs, custom kernels, and engine-specific defaults in logit processing. Our findings identify the inference backend as a previously unreported but consequential hyperparameter in the evaluation of LLM and advocate standardized reporting of inference stacks to improve the reproducibility and interpretability of benchmark comparisons.

The growing demand for Large Language Models (LLMs) across diverse applications has prompted a paradigm shift in the design of deep learning serving systems. Deploying LLMs, especially in multi-tenant environments, presents considerable challenges due to their high computational and memory demands. We present BlockLLM, a serving system that exploits the potential of sharing components among fine-tuned LLM models to offer an efficient and flexible solution for LLM workloads. BlockLLM partitions the models into finer-grained blocks to enable the reuse of model components and independent provisioning to improve the computation efficiency. BlockLLM consists of an offline block zoo, for storing the blocks, and an online system to serve the requests through chains of blocks. It offers multi-fold flexibility: (1) Adaptive assembly of block chains on-the-fly is achieved with the help of equivalence evaluation among blocks in the zoo. (2) We enable per-block batch size and configure best-effort KV cache coordination at individual block level. (3) We adopt speculative execution and locality-aware block placement to mitigate the communication costs from dynamic block resource allocation. Our evaluation demonstrates that BlockLLM reduces memory and storage footprints and improves computation efficiency, outperforming existing serving approach in 95\%ile latency and GPU utilization by 33.5\% and 20.1\%, respectively.

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and heterogeneous workloads -- introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) latency and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2x and achieving 3.2-4.5x higher throughput while meeting service-level objectives (SLOs).

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-scale models and infrequent requests. While existing solutions follow exclusive GPU deployment, we take a step back to explore modern platforms and find that: Emerging CPU architectures with built-in accelerators are capable of serving LLMs but remain underutilized, and both CPUs and GPUs can accommodate multiple LLMs simultaneously. We propose LLM-Mesh, a serverless inference scheme for small-to-mid-sized LLMs that enables elastic sharing across heterogeneous hardware. LLM-Mesh tackles three fundamental challenges: (1) precise, fine-grained compute resource allocation at token-level to handle fluctuating computational demands; (2) a coordinated and forward-looking memory scaling mechanism to detect out-of-memory hazards and reduce operational overhead; and (3) a dual approach that reduces resource fragmentation through proactive preemption and reactive bin-packing. Experimental results on 4 32-core CPUs and 4 A100 GPUs show that LLM-Meshimproves service capacity by 44% - 63% through sharing, while further leveraging CPUs boosts this to 91% - 159%.

The immense evolution in Large Language Models (LLMs) has underscored the importance of massive, diverse, and high-quality data. Despite this, existing open-source tools for LLM data processing remain limited and mostly tailored to specific datasets, with an emphasis on the reproducibility of released data over adaptability and usability, inhibiting potential applications. In response, we propose a one-stop, powerful yet flexible and user-friendly LLM data processing system named Data-Juicer. Our system offers over 50 built-in versatile operators and pluggable tools, which synergize modularity, composability, and extensibility dedicated to diverse LLM data processing needs. By incorporating visualized and automatic evaluation capabilities, Data-Juicer enables a timely feedback loop to accelerate data processing and gain data insights. To enhance usability, Data-Juicer provides out-of-the-box components for users with various backgrounds, and fruitful data recipes for LLM pre-training and post-tuning usages. Further, we employ multi-facet system optimization and seamlessly integrate Data-Juicer with both LLM and distributed computing ecosystems, to enable efficient and scalable data processing. Empirical validation of the generated data recipes reveals considerable improvements in LLaMA performance for various pre-training and post-tuning cases, demonstrating up to 7.45% relative improvement of averaged score across 16 LLM benchmarks and 16.25% higher win rate using pair-wise GPT-4 evaluation. The system's efficiency and scalability are also validated, supported by up to 88.7% reduction in single-machine processing time, 77.1% and 73.1% less memory and CPU usage respectively, and 7.91x processing acceleration when utilizing distributed computing ecosystems. Our system, data recipes, and multiple tutorial demos are released, calling for broader research centered on LLM data.

Current LLM-based coding agents follow a serial execution paradigm: the model first generates the complete code, then invokes an interpreter to execute it. This sequential workflow leaves the executor idle during generation and the generator idle during execution, resulting in unnecessary end-to-end latency. We observe that, unlike human developers, LLMs produce code tokens sequentially without revision, making it possible to execute code as it is being generated. We formalize this parallel execution paradigm, modeling it as a three-stage pipeline of generation, detection, and execution, and derive closed-form latency bounds that characterize its speedup potential and operating regimes. We then present Eager, a concrete implementation featuring AST-based chunking, dynamic batching with gated execution, and early error interruption. We evaluate Eager across four benchmarks, seven LLMs, and three execution environments. Results show that Eager reduces the non-overlapped execution latency by up to 99.9% and the end-to-end latency by up to 55% across seven LLMs and four benchmarks.

Large language models (LLMs) have demonstrated remarkable capabilities in chain of thought (CoT) reasoning. However, the current LLM reasoning paradigm initiates thinking only after the entire input is available, which introduces unnecessary latency and weakens attention to earlier information in dynamic scenarios. Inspired by human cognition of thinking while reading, we first design a \textbf{streaming thinking} paradigm for LLMs, where reasoning unfolds in the order of input and further adjusts its depth once reading is complete. We instantiate this paradigm with StreamingThinker, a framework that enables LLMs to think while reading through the integration of streaming CoT generation, streaming-constraint training, and streaming parallel inference. Specifically, StreamingThinker employs streaming reasoning units with quality control for CoT generation, enforces order-preserving reasoning through streaming attention masks and position encoding, and leverages parallel KV caches that decouple input encoding from reasoning generation, thereby ensuring alignment and enabling true concurrency. We evaluate StreamingThinker on the Qwen3 model family across math reasoning, logical reasoning, and context-based QA reasoning tasks. Experimental results show that the StreamingThinker preserves performance comparable to batch thinking, while yielding an 80\% reduction in token waiting before the onset of reasoning and a more than 60\% reduction in time-level latency for producing the final answer, demonstrating the effectiveness of the streaming paradigm for LLM reasoning. Code is publicly available at https://github.com/EIT-NLP/StreamingLLM/tree/main/StreamingThinker.

Large Language Models (LLMs) are becoming integral to daily life, showcasing their vast potential across various Natural Language Processing (NLP) tasks. Beyond NLP, LLMs are increasingly used in software development tasks, such as code completion, modification, bug fixing, and code translation. Software engineers widely use tools like GitHub Copilot and Amazon Q, streamlining workflows and automating tasks with high accuracy. While the resource and energy intensity of LLM training is often highlighted, inference can be even more resource-intensive over time, as it's a continuous process with a high number of invocations. Therefore, developing resource-efficient alternatives for LLM inference is crucial for sustainability. This work proposes GREEN-CODE, a framework for energy-aware code generation in LLMs. GREEN-CODE performs dynamic early exit during LLM inference. We train a Reinforcement Learning (RL) agent that learns to balance the trade-offs between accuracy, latency, and energy consumption. Our approach is evaluated on two open-source LLMs, Llama 3.2 3B and OPT 2.7B, using the JavaCorpus and PY150 datasets. Results show that our method reduces the energy consumption between 23-50 % on average for code generation tasks without significantly affecting accuracy.

The customization of large language models (LLMs) for user-specified tasks gets important. However, maintaining all the customized LLMs on cloud servers incurs substantial memory and computational overheads, and uploading user data can also lead to privacy concerns. On-device LLMs can offer a promising solution by mitigating these issues. Yet, the performance of on-device LLMs is inherently constrained by the limitations of small-scaled models. To overcome these restrictions, we first propose Crayon, a novel approach for on-device LLM customization. Crayon begins by constructing a pool of diverse base adapters, and then we instantly blend them into a customized adapter without extra training. In addition, we develop a device-server hybrid inference strategy, which deftly allocates more demanding queries or non-customized tasks to a larger, more capable LLM on a server. This ensures optimal performance without sacrificing the benefits of on-device customization. We carefully craft a novel benchmark from multiple question-answer datasets, and show the efficacy of our method in the LLM customization.

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.

The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc scripts and loosely specified workflows, which lack principled abstractions, hinder reproducibility, and offer limited support for model-in-the-loop data generation. To address these challenges, we present DataFlow, a unified and extensible LLM-driven data preparation framework. DataFlow is designed with system-level abstractions that enable modular, reusable, and composable data transformations, and provides a PyTorch-style pipeline construction API for building debuggable and optimizable dataflows. The framework consists of nearly 200 reusable operators and six domain-general pipelines spanning text, mathematical reasoning, code, Text-to-SQL, agentic RAG, and large-scale knowledge extraction. To further improve usability, we introduce DataFlow-Agent, which automatically translates natural-language specifications into executable pipelines via operator synthesis, pipeline planning, and iterative verification. Across six representative use cases, DataFlow consistently improves downstream LLM performance. Our math, code, and text pipelines outperform curated human datasets and specialized synthetic baselines, achieving up to +3\% execution accuracy in Text-to-SQL over SynSQL, +7\% average improvements on code benchmarks, and 1--3 point gains on MATH, GSM8K, and AIME. Moreover, a unified 10K-sample dataset produced by DataFlow enables base models to surpass counterparts trained on 1M Infinity-Instruct data. These results demonstrate that DataFlow provides a practical and high-performance substrate for reliable, reproducible, and scalable LLM data preparation, and establishes a system-level foundation for future data-centric AI development.

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process long video sequences and demonstrate remarkable performance. Nonetheless, studies predominantly focus on offline video question answering, neglecting memory usage and response speed that are essential in various real-world applications, such as Deepseek services, autonomous driving, and robotics. To mitigate these challenges, we propose LiveVLM, a training-free framework specifically designed for streaming, online video understanding and real-time interaction. Unlike existing works that process videos only after one question is posed, LiveVLM constructs an innovative streaming-oriented KV cache to process video streams in real-time, retain long-term video details and eliminate redundant KVs, ensuring prompt responses to user queries. For continuous video streams, LiveVLM generates and compresses video key-value tensors (video KVs) to reserve visual information while improving memory efficiency. Furthermore, when a new question is proposed, LiveVLM incorporates an online question-answering process that efficiently fetches both short-term and long-term visual information, while minimizing interference from redundant context. Extensive experiments demonstrate that LiveVLM enables the foundation LLaVA-OneVision model to process 44times number of frames on the same device, and achieves up to 5times speedup in response speed compared with SoTA online methods at an input of 256 frames, while maintaining the same or better model performance.

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the streaming video understanding capabilities of MLLMs. StreamingBench assesses three core aspects of streaming video understanding: (1) real-time visual understanding, (2) omni-source understanding, and (3) contextual understanding. The benchmark consists of 18 tasks, featuring 900 videos and 4,500 human-curated QA pairs. Each video features five questions presented at different time points to simulate a continuous streaming scenario. We conduct experiments on StreamingBench with 13 open-source and proprietary MLLMs and find that even the most advanced proprietary MLLMs like Gemini 1.5 Pro and GPT-4o perform significantly below human-level streaming video understanding capabilities. We hope our work can facilitate further advancements for MLLMs, empowering them to approach human-level video comprehension and interaction in more realistic scenarios.

In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several challenges arise. Firstly, increasing the number of GPUs may lead to a decrease in inference speed due to heightened communication overhead, while an inadequate number of GPUs can lead to out-of-memory errors. Secondly, different deployment strategies need to be evaluated to guarantee optimal utilization and minimal inference latency. Lastly, inefficient orchestration of inference queries can easily lead to significant Service Level Objective (SLO) violations. Lastly, inefficient orchestration of inference queries can easily lead to significant Service Level Objective (SLO) violations. To address these challenges, we propose a Unified and Efficient approach for Large Language Model inference serving (UELLM), which consists of three main components: 1) resource profiler, 2) batch scheduler, and 3) LLM deployer. UELLM minimizes resource overhead, reduces inference latency, and lowers SLO violation rates. Compared with state-of-the-art (SOTA) techniques, UELLM reduces the inference latency by 72.3% to 90.3%, enhances GPU utilization by 1.2X to 4.1X, and increases throughput by 1.92X to 4.98X, it can also serve without violating the inference latency SLO.

We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle with long videos, as they must process entire videos before responding to queries, and repeat this process for each new question. In contrast, our approach analyzes long videos in a streaming manner, allowing for prompt responses as soon as user queries are received. Building on a common Video-LLM, we first incorporate a sliding-window attention mechanism, ensuring that input frames attend to a limited number of preceding frames, thereby reducing computational overhead. To prevent information loss, we store processed video key-value caches (KV-Caches) in RAM and disk, reloading them into GPU memory as needed. Additionally, we introduce a retrieval method that leverages an external retriever or the parameters within Video-LLMs to retrieve only query-relevant KV-Caches, ensuring both efficiency and accuracy in question answering. ReKV enables the separation of video encoding and question-answering across different processes and GPUs, significantly enhancing the efficiency of StreamingVQA. Through comprehensive experimentation, we validate the efficacy and practicality of our approach, which significantly boosts efficiency and enhances applicability over existing VideoQA models.

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across all users and requests. We find that this strategy not only leads to strong prefill-decoding interferences but also couples the resource allocation and parallelism plans for both phases. LLM applications often emphasize individual latency for each phase: time to first token (TTFT) for the prefill phase and time per output token (TPOT) of each request for the decoding phase. In the presence of stringent latency requirements, existing systems have to prioritize one latency over the other, or over-provision compute resources to meet both. DistServe assigns prefill and decoding computation to different GPUs, hence eliminating prefill-decoding interferences. Given the application's TTFT and TPOT requirements, DistServe co-optimizes the resource allocation and parallelism strategy tailored for each phase. DistServe also places the two phases according to the serving cluster's bandwidth to minimize the communication caused by disaggregation. As a result, DistServe significantly improves LLM serving performance in terms of the maximum rate that can be served within both TTFT and TPOT constraints on each GPU. Our evaluations show that on various popular LLMs, applications, and latency requirements, DistServe can serve 4.48x more requests or 10.2x tighter SLO, compared to state-of-the-art systems, while staying within latency constraints for > 90% of requests.

Large language models (LLMs) are increasingly deployed in specialized production data processing pipelines across diverse domains -- such as finance, marketing, and e-commerce. However, when running them in production across many inputs, they often fail to follow instructions or meet developer expectations. To improve reliability in these applications, creating assertions or guardrails for LLM outputs to run alongside the pipelines is essential. Yet, determining the right set of assertions that capture developer requirements for a task is challenging. In this paper, we introduce PROMPTEVALS, a dataset of 2087 LLM pipeline prompts with 12623 corresponding assertion criteria, sourced from developers using our open-source LLM pipeline tools. This dataset is 5x larger than previous collections. Using a hold-out test split of PROMPTEVALS as a benchmark, we evaluated closed- and open-source models in generating relevant assertions. Notably, our fine-tuned Mistral and Llama 3 models outperform GPT-4o by 20.93% on average, offering both reduced latency and improved performance. We believe our dataset can spur further research in LLM reliability, alignment, and prompt engineering.

Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives continuously and queries probe an ever-growing context, this cost is prohibitive. We introduce a data-driven computational model centred on stateful sessions: a persistent KV cache advanced incrementally as new data arrives, so prefill is moved off the critical path and query latency becomes O(|q|), independent of accumulated context size. Building on this, Flash Queries reclaim idle GPU cycles between data arrivals to pre-evaluate registered questions and return cached answers before the user asks, a pattern that is structurally impossible in stateless engines because they discard intermediate state between requests. A multi-tenant continuous-batching scheduler with cell-budget admission and prefix-aware grouped prefill lets dozens of stateful sessions coexist on a single GPU while preserving full quadratic self-attention. On streaming market-data benchmarks the reference implementation achieves up to 5.9x speedup over conventional inference engines (vLLM, SGLang, TensorRT-LLM, llama.cpp), holding query latency constant as accumulated context grows.

Recent advancements in speech-to-speech dialogue systems leverage LLMs for multimodal interactions, yet they remain hindered by fine-tuning requirements, high computational overhead, and text-speech misalignment. Existing speech-enabled LLMs often degrade conversational quality by modifying the LLM, thereby compromising its linguistic capabilities. In contrast, we propose LLMVoX, a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming TTS system that generates high-quality speech with low latency, while fully preserving the capabilities of the base LLM. Our approach achieves a significantly lower Word Error Rate compared to speech-enabled LLMs, while operating at comparable latency and UTMOS score. By decoupling speech synthesis from LLM processing via a multi-queue token streaming system, LLMVoX supports seamless, infinite-length dialogues. Its plug-and-play design also facilitates extension to various tasks with different backbones. Furthermore, LLMVoX generalizes to new languages with only dataset adaptation, attaining a low Character Error Rate on an Arabic speech task. Additionally, we have integrated LLMVoX with a Vision-Language Model to create an omni-model with speech, text, and vision capabilities, without requiring additional multimodal training. Our code base and project page is available at https://mbzuai-oryx.github.io/LLMVoX .

Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions that generate video progressively, chunk by chunk. Unlike offline video generation or typical LLM serving, streaming video generation must preserve session state across active and idle periods, repeatedly schedule ongoing sessions, and deliver each chunk under a tight latency target. This creates two key serving challenges in multi-user, multi-GPU environments: session duration heterogeneity, where long-running sessions make placement decisions suboptimal over time, and temporal user-demand heterogeneity, where the number of active sessions fluctuates sharply across bursts and idle periods. We present TurboServe, the first serving system designed specifically for streaming video generation workloads. TurboServe formulates serving as an online scheduling problem that jointly coordinates session placement and GPU provisioning. Its closed-loop scheduling algorithm combines a migration-aware placement controller, which rebalances sessions across GPUs to reduce the maximum per-chunk latency, with a load-driven autoscaling controller, which adapts the GPU budget to workload variation for improved cost efficiency. To support these decisions at runtime, TurboServe implements coalesced chunk processing for batching concurrent active sessions on the same GPU, GPU-CPU offloading for session suspension and resumption, and NCCL-based GPU-GPU migration for online rebalancing. We evaluate TurboServe on real-world production traces from Shengshu Technology across multiple model sizes and GPU clusters with up to 64 NVIDIA B300 GPUs. Compared with baseline serving configurations, TurboServe reduces worst-case per-chunk latency by 37.5% and total GPU operating cost by 37.2% on average. Our code is publicly available at https://github.com/shengshu-ai/TurboServe.

Recent advancements in large language models (LLMs) have driven a revolutionary paradigm shift in process automation from Robotic Process Automation to Agentic Process Automation by automating the workflow orchestration procedure based on LLMs. However, existing LLMs (even the advanced OpenAI GPT-4o) are confined to achieving satisfactory capability in workflow orchestration. To address this limitation, we present WorkflowLLM, a data-centric framework elaborately designed to enhance the capability of LLMs in workflow orchestration. It first constructs a large-scale fine-tuning dataset WorkflowBench with 106,763 samples, covering 1,503 APIs from 83 applications across 28 categories. Specifically, the construction process can be divided into three phases: (1) Data Collection: we collect real-world workflow data from Apple Shortcuts and RoutineHub, transcribing them into Python-style code. We further equip them with generated hierarchical thought via ChatGPT. (2) Query Expansion: we prompt ChatGPT to generate more task queries to enrich the diversity and complexity of workflows. (3) Workflow Generation: we leverage an annotator model trained on collected data to generate workflows for synthesized queries. Finally, we merge the synthetic samples that pass quality confirmation with the collected samples to obtain the WorkflowBench. Based on WorkflowBench, we fine-tune Llama-3.1-8B to obtain WorkflowLlama. Our experiments show that WorkflowLlama demonstrates a strong capacity to orchestrate complex workflows, while also achieving notable generalization performance on previously unseen APIs. Additionally, WorkflowBench exhibits robust zero-shot generalization capabilities on an out-of-distribution task planning dataset, T-Eval. Our data and code are available at https://github.com/OpenBMB/WorkflowLLM.

Large language models (LLMs) are known for their exceptional performance across a range of natural language processing tasks, but their deployment comes at a high computational and financial cost. On the other hand, smaller language models (SLMs), which can be deployed on lower-cost edge devices, struggle to match the performance of their larger counterparts. This paper presents a novel hybrid inference approach that leverages the strengths of both model types while minimizing reliance on costly cloud-based LLMs. Unlike existing methods that route entire queries to either an SLM or a cloud LLM, our approach introduces a reward-based mechanism to dynamically determine the involvement of the cloud LLM during token generation. Specifically, each token predicted by the SLM is evaluated against a reward score, and only when this score falls below a certain threshold is the cloud LLM consulted for assistance in the next token prediction. This method not only reduces the traffic to the cloud LLM, thereby lowering costs, but also allows for flexible control over response quality depending on the reward score threshold. Experimental results demonstrate that our approach significantly reduces cloud LLM usage with minimal impact on overall response quality, offering a cost-effective solution for deploying high-performance language models

Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unauthorized training of LLMs on copyrighted text to infringe such IP. However, existing text watermarking methods are not robust enough against such attacks nor scalable to millions of users for practical implementation. In this paper, we propose Waterfall, the first training-free framework for robust and scalable text watermarking applicable across multiple text types (e.g., articles, code) and languages supportable by LLMs, for general text and LLM data provenance. Waterfall comprises several key innovations, such as being the first to use LLM as paraphrasers for watermarking along with a novel combination of techniques that are surprisingly effective in achieving robust verifiability and scalability. We empirically demonstrate that Waterfall achieves significantly better scalability, robust verifiability, and computational efficiency compared to SOTA article-text watermarking methods, and showed how it could be directly applied to the watermarking of code. We also demonstrated that Waterfall can be used for LLM data provenance, where the watermarks of LLM training data can be detected in LLM output, allowing for detection of unauthorized use of data for LLM training and potentially enabling model-centric watermarking of open-sourced LLMs which has been a limitation of existing LLM watermarking works. Our code is available at https://github.com/aoi3142/Waterfall.

The integration of large language model (LLM) and data management (DATA) is rapidly redefining both domains. In this survey, we comprehensively review the bidirectional relationships. On the one hand, DATA4LLM, spanning large-scale data processing, storage, and serving, feeds LLMs with high quality, diversity, and timeliness of data required for stages like pre-training, post-training, retrieval-augmented generation, and agentic workflows: (i) Data processing for LLMs includes scalable acquisition, deduplication, filtering, selection, domain mixing, and synthetic augmentation; (ii) Data Storage for LLMs focuses on efficient data and model formats, distributed and heterogeneous storage hierarchies, KV-cache management, and fault-tolerant checkpointing; (iii) Data serving for LLMs tackles challenges in RAG (e.g., knowledge post-processing), LLM inference (e.g., prompt compression, data provenance), and training strategies (e.g., data packing and shuffling). On the other hand, in LLM4DATA, LLMs are emerging as general-purpose engines for data management. We review recent advances in (i) data manipulation, including automatic data cleaning, integration, discovery; (ii) data analysis, covering reasoning over structured, semi-structured, and unstructured data, and (iii) system optimization (e.g., configuration tuning, query rewriting, anomaly diagnosis), powered by LLM techniques like retrieval-augmented prompting, task-specialized fine-tuning, and multi-agent collaboration.

Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response quality and minimize cost and latency. However, the challenges involve: (1) dynamic trade-offs among quality, cost, and latency; (2) enabling continual learning in deployed systems; and (3) navigating a varying (e.g., new LLM addition or old LLM removal) set of LLM candidates over time. To bridge these gaps, we develop MixLLM, a dynamic contextual-bandit-based routing system for query-LLM assignment. Specifically, we first leverage query tags to enhance query embeddings for the routing task. Next, we design lightweight prediction models to estimate the response qualities and costs of queries over LLMs. We then devise a meta-decision maker to choose the query-LLM assignments to best tradeoff response quality, cost, and latency. Finally, the system benefits from continual training, allowing it to adapt to evolving queries and user feedback over time. Our extensive experiments show that MixLLM achieves the best trade-offs in response quality, cost, and latency (97.25% of GPT-4's quality at 24.18% of the cost under the time constraint).

With the ubiquitous use of modern large language models (LLMs) across industries, the inference serving for these models is ever expanding. Given the high compute and memory requirements of modern LLMs, more and more top-of-the-line GPUs are being deployed to serve these models. Energy availability has come to the forefront as the biggest challenge for data center expansion to serve these models. In this paper, we present the trade-offs brought up by making energy efficiency the primary goal of LLM serving under performance SLOs. We show that depending on the inputs, the model, and the service-level agreements, there are several knobs available to the LLM inference provider to use for being energy efficient. We characterize the impact of these knobs on the latency, throughput, as well as the energy. By exploring these trade-offs, we offer valuable insights into optimizing energy usage without compromising on performance, thereby paving the way for sustainable and cost-effective LLM deployment in data center environments.

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct characteristics of these phases, leading to significant interference. To mitigate interference, our insight is to carefully schedule and group inference requests based on their characteristics. We realize this idea in TetriInfer through three pillars. First, it partitions prompts into fixed-size chunks so that the accelerator always runs close to its computationsaturated limit. Second, it disaggregates prefill and decode instances so each can run independently. Finally, it uses a smart two-level scheduling algorithm augmented with predicted resource usage to avoid decode scheduling hotspots. Results show that TetriInfer improves time-to-first-token (TTFT), job completion time (JCT), and inference efficiency in turns of performance per dollar by a large margin, e.g., it uses 38% less resources all the while lowering average TTFT and average JCT by 97% and 47%, respectively.

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under intermittent connectivity, sub-second latency budgets, data-residency constraints, or sustained high-volume inference. On-device deployment is in turn constrained by limited computation and memory. No single endpoint can deliver high-quality service across this spectrum. This article focuses on collaborative intelligence, a paradigm in which multiple independent LLMs distributed across device and cloud endpoints collaborate at the task level through natural language or structured messages. Such collaboration strives for superior response quality under heterogeneous resource constraints spanning computation, memory, communication, and cost across network tiers. We present collaborative inference along two complementary and composable dimensions: vertical device-cloud collaboration and horizontal multi-agent collaboration, which can be combined into hybrid topologies in practice. We then examine learning to collaborate, addressing the training of routing policies and the development of cooperative capabilities among LLMs. Finally, we identify open research challenges including scaling under resource heterogeneity and trustworthy collaborative intelligence.

Routing large language models (LLMs) is a new paradigm that uses a router to recommend the best LLM from a pool of candidates for a given input. In this paper, our comprehensive analysis with more than 8,500 LLMs reveals a novel model-level scaling up phenomenon in Routing LLMs, i.e., a capable router can significantly enhance the performance of this paradigm as the number of candidates increases. This improvement can even surpass the performance of the best single model in the pool and many existing strong LLMs, confirming it a highly promising paradigm. However, the lack of comprehensive and open-source benchmarks for Routing LLMs has hindered the development of routers. In this paper, we introduce RouterEval, a benchmark tailored for router research, which includes over 200,000,000 performance records for 12 popular LLM evaluations across various areas such as commonsense reasoning, semantic understanding, etc., based on over 8,500 various LLMs. Using RouterEval, extensive evaluations of existing Routing LLM methods reveal that most still have significant room for improvement. See https://github.com/MilkThink-Lab/RouterEval for all data, code and tutorial.

As the range of applications for Large Language Models (LLMs) continues to grow, the demand for effective serving solutions becomes increasingly critical. Despite the versatility of LLMs, no single model can optimally address all tasks and applications, particularly when balancing performance with cost. This limitation has led to the development of LLM routing systems, which combine the strengths of various models to overcome the constraints of individual LLMs. Yet, the absence of a standardized benchmark for evaluating the performance of LLM routers hinders progress in this area. To bridge this gap, we present RouterBench, a novel evaluation framework designed to systematically assess the efficacy of LLM routing systems, along with a comprehensive dataset comprising over 405k inference outcomes from representative LLMs to support the development of routing strategies. We further propose a theoretical framework for LLM routing, and deliver a comparative analysis of various routing approaches through RouterBench, highlighting their potentials and limitations within our evaluation framework. This work not only formalizes and advances the development of LLM routing systems but also sets a standard for their assessment, paving the way for more accessible and economically viable LLM deployments. The code and data are available at https://github.com/withmartian/routerbench.

Large language models (LLM) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like LaPM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessitating specialized models. Therefore, Small Language Models (SLMs) are increasingly favored for their low inference latency, cost-effectiveness, efficient development, and easy customization and adaptability. These models are particularly well-suited for resource-limited environments and domain knowledge acquisition, addressing LLMs' challenges and proving ideal for applications that require localized data handling for privacy, minimal inference latency for efficiency, and domain knowledge acquisition through lightweight fine-tuning. The rising demand for SLMs has spurred extensive research and development. However, a comprehensive survey investigating issues related to the definition, acquisition, application, enhancement, and reliability of SLM remains lacking, prompting us to conduct a detailed survey on these topics. The definition of SLMs varies widely, thus to standardize, we propose defining SLMs by their capability to perform specialized tasks and suitability for resource-constrained settings, setting boundaries based on the minimal size for emergent abilities and the maximum size sustainable under resource constraints. For other aspects, we provide a taxonomy of relevant models/methods and develop general frameworks for each category to enhance and utilize SLMs effectively.

Multi-agent LLM systems usually collaborate by exchanging natural-language messages. This interface is simple and interpretable, but it forces each sender's intermediate computation to be serialized into tokens and then reprocessed by the receiver, thereby increasing the generated-token cost, prefill overhead, and KV-cache memory. We study an alternative communication interface: instead of appending a sender's message to the receiver's context, compile the sender's hidden states into a transient, receiver-specific weight perturbation. We introduce TFlow (Thought Flow), a weight-space communication framework for a known and fixed receiver architecture. For each query, frozen role-prompted sender agents process the input, and a learned parameter generator maps their internal activations into low-rank LoRA perturbations targeting the receiver's modules. These perturbations are fused and applied only during the receiver's generation, enabling instance-level adaptation without permanently changing the model or enlarging the receiver's text context. With three Qwen3-4B agents, TFlow improves over a standalone receiver by up to 8.5 accuracy points across five benchmarks while reducing processed tokens by up to 32.69%. Compared with a text-based three-agent baseline, it reduces total processed tokens by up to 83.27% and the wall-clock inference time by up to 4.6times, while maintaining competitive accuracy on four of five benchmarks. These results suggest that transient low-rank weight perturbations can serve as an executable communication medium for efficient multi-agent LLM collaboration.

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing LS time-to-first-token (TTFT). Our approach removes iteration-level scheduling constraints, enabling the scheduler to preempt jobs at any layer based on priority. Evaluations on an Nvidia A100 GPU show that QLLM significantly improves performance. It reduces LS TTFT by an average of 65.5times and meets the SLO at up to 7 requests/sec, whereas the baseline fails to do so under the tested workload. Additionally, it cuts LS turnaround time by up to 12.8times without impacting throughput. QLLM is modular, extensible, and seamlessly integrates with Hugging Face MoE models.

Recent advancements in large language models (LLMs) have prompted interest in deploying these models on mobile devices to enable new applications without relying on cloud connectivity. However, the efficiency constraints of deploying LLMs on resource-limited devices present significant challenges. In this paper, we conduct a comprehensive measurement study to evaluate the efficiency tradeoffs between mobile-based, edge-based, and cloud-based deployments for LLM applications. We implement AutoLife-Lite, a simplified LLM-based application that analyzes smartphone sensor data to infer user location and activity contexts. Our experiments reveal that: (1) Only small-size LLMs (<4B parameters) can run successfully on powerful mobile devices, though they exhibit quality limitations compared to larger models; (2) Model compression is effective in lower the hardware requirement, but may lead to significant performance degradation; (3) The latency to run LLMs on mobile devices with meaningful output is significant (>30 seconds), while cloud services demonstrate better time efficiency (<10 seconds); (4) Edge deployments offer intermediate tradeoffs between latency and model capabilities, with different results on CPU-based and GPU-based settings. These findings provide valuable insights for system designers on the current limitations and future directions for on-device LLM applications.

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows, existing merging implementations treat model parameters as unstructured files and execute merges in a stateless, one-shot manner, leading to excessive disk I/O, redundant parameter scans, and poor scalability. In this paper, we present MergePipe, a parameter management system for scalable LLM merging. MergePipe is the first system that treats LLM merging as a data management and execution problem, and introduces a catalog-driven abstraction over model parameters, merge plans, and execution lineage. At its core, MergePipe employs a cost-aware planner that explicitly models expert parameter I/O and enforces user-specified I/O budgets, followed by a streaming execution engine that materializes merged models under transactional guarantees. Our key insight is that while base model reads and output writes are unavoidable, expert parameter reads dominate merge cost and constitute the primary optimization target. By making expert access budget-aware throughout planning and execution, MergePipe mitigates the O(K) I/O growth of naive pipelines and achieves predictable scaling behavior. Experiments show that MergePipe reduces total I/O by up to an order of magnitude and delivers up to 11times end-to-end speedups (up to 90\% wall-time reduction) over state-of-the-art LLM merging pipelines.

Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying test-time scaling methods incurs unacceptable response latency. To address this trade-off, we propose Video Streaming Thinking (VST), a novel paradigm for streaming video understanding. It supports a thinking while watching mechanism, which activates reasoning over incoming video clips during streaming. This design improves timely comprehension and coherent cognition while preserving real-time responsiveness by amortizing LLM reasoning latency over video playback. Furthermore, we introduce a comprehensive post-training pipeline that integrates VST-SFT, which structurally adapts the offline VideoLLM to causal streaming reasoning, and VST-RL, which provides end-to-end improvement through self-exploration in a multi-turn video interaction environment. Additionally, we devise an automated training-data synthesis pipeline that uses video knowledge graphs to generate high-quality streaming QA pairs, with an entity-relation grounded streaming Chain-of-Thought to enforce multi-evidence reasoning and sustained attention to the video stream. Extensive evaluations show that VST-7B performs strongly on online benchmarks, e.g. 79.5% on StreamingBench and 59.3% on OVO-Bench. Meanwhile, VST remains competitive on offline long-form or reasoning benchmarks. Compared with Video-R1, VST responds 15.7 times faster and achieves +5.4% improvement on VideoHolmes, demonstrating higher efficiency and strong generalization across diverse video understanding tasks. Code, data, and models will be released at https://github.com/1ranGuan/VST.

The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.

The rapid advancement of large language models (LLMs) has created a vibrant ecosystem of diverse architectures, each with unique strengths due to differences in design, training data, and objectives. However, most applications still rely on a single backend model, limiting coverage of capabilities and leading to inefficiencies in performance and token cost when tackling complex tasks. We highlight an underexploited opportunity: LLM routing data, produced when hosting platforms route diverse queries to different models, which can reveal comparative strengths across tasks. To address this, we propose FusionBench, a comprehensive routing benchmark covering 14 tasks across five domains with 20 open-source LLMs (8B to 671B parameters), capturing 103M tokens and summarizing reusable thought templates from top models. Building on this, we introduce FusionFactory, a systematic fusion framework with three levels: (1) query-level fusion, tailoring routers for each query using both direct responses and reasoning-augmented outputs; (2) thought-level fusion, leveraging abstract templates derived from top-performing LLMs' answers to similar queries; and (3) model-level fusion, transferring capabilities between models via distillation, using top responses or highest judge scores as training data. Experiments show FusionFactory consistently outperforms the best individual LLM across all 14 benchmarks, with optimal fusion configurations varying by benchmark, demonstrating the value of systematic LLM fusion in harnessing complementary strengths and improving overall performance.

Large Language Models (LLMs), such as ChatGPT, LLaMA, GLM, and PaLM, have exhibited remarkable performances across various tasks in recent years. However, LLMs face two main challenges in real-world applications. One challenge is that training LLMs consumes vast computing resources, preventing LLMs from being adopted by small and medium-sized enterprises with limited computing resources. Another is that training LLM requires a large amount of high-quality data, which are often scattered among enterprises. To address these challenges, we propose FATE-LLM, an industrial-grade federated learning framework for large language models. FATE-LLM (1) facilitates federated learning for large language models (coined FedLLM); (2) promotes efficient training of FedLLM using parameter-efficient fine-tuning methods; (3) protects the intellectual property of LLMs; (4) preserves data privacy during training and inference through privacy-preserving mechanisms. We release the code of FATE-LLM at https://github.com/FederatedAI/FATE-LLM to facilitate the research of FedLLM and enable a broad range of industrial applications.

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with massive operations and perform inference in the auto-regressive mode, making it a challenging task to design a system with high efficiency. In this paper, we propose an efficient LLM inference solution with low latency and high throughput. Firstly, we simplify the LLM decoder layer by fusing data movement and element-wise operations to reduce the memory access frequency and lower system latency. We also propose a segment KV cache policy to keep key/value of the request and response tokens in separate physical memory for effective device memory management, helping enlarge the runtime batch size and improve system throughput. A customized Scaled-Dot-Product-Attention kernel is designed to match our fusion policy based on the segment KV cache solution. We implement our LLM inference solution on Intel GPU and publish it publicly. Compared with the standard HuggingFace implementation, the proposed solution achieves up to 7x lower token latency and 27x higher throughput for some popular LLMs on Intel GPU.

Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.

As Large Language Models (LLMs) become increasingly prevalent in various domains, their ability to process inputs of any length and maintain a degree of memory becomes essential. However, the one-off input of overly long texts is limited, as studies have shown that when input lengths exceed the LLMs' pre-trained text length, there is a dramatic decline in text generation capabilities. Moreover, simply extending the length of pre-training texts is impractical due to the difficulty in obtaining long text data and the substantial memory consumption costs this would entail for LLMs. Recent efforts have employed streaming inputs to alleviate the pressure of excessively long text inputs, but this approach can significantly impair the model's long-term memory capabilities. Motivated by this challenge, we introduce Streaming Infinite Retentive LLM (SirLLM), which allows LLMs to maintain longer memory during infinite-length dialogues without the need for fine-tuning. SirLLM utilizes the Token Entropy metric and a memory decay mechanism to filter key phrases, endowing LLMs with both long-lasting and flexible memory. We designed three distinct tasks and constructed three datasets to measure the effectiveness of SirLLM from various angles: (1) DailyDialog; (2) Grocery Shopping; (3) Rock-Paper-Scissors. Our experimental results robustly demonstrate that SirLLM can achieve stable and significant improvements across different LLMs and tasks, compellingly proving its effectiveness. When having a coversation, "A sir could forget himself," but SirLLM never does! Our code is publicly available at https://github.com/Zoeyyao27/SirLLM

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like document summarization. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving latency requirements. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation, without compromising online serving latency. Our evaluation on production workloads shows that HyGen achieves up to 3.87x overall throughput and 5.84x offline throughput gains over online and hybrid serving baselines, respectively, while strictly satisfying latency SLOs.

Increasing demand for Large Language Models (LLMs) services imposes substantial deployment and computation costs on providers. LLM routing offers a cost-efficient solution by directing queries to the optimal LLM based on model and query features. However, existing works primarily focus on offline scenarios and struggle to adapt to online settings with high query volume and constrained token budgets. In this work, we introduce the first training-free algorithm for online routing scenarios. Our algorithm leverages approximate nearest neighbor search to efficiently estimate query features and performs a one-time optimization over a small set of initial queries to learn a routing strategy that guides future routing. We provide theoretical guarantees demonstrating that our algorithm achieves a competitive ratio of 1 - o(1) under natural assumptions, which is further validated by extensive experiments across 3 benchmark datasets and 8 baselines, showing an average improvement of 3.55times in overall performance, 1.85times in cost efficiency, and nearly 4.25times in throughput. Our code is available at https://github.com/fzwark/PORT.

As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation requires a synchronized update operation among each partial softmax result, leading to ~20% overheads for the attention computation in LLMs. (2) Under-utilized computation of flat GEMM. The shape of matrices performing GEMM in LLM inference is flat, leading to under-utilized computation and >50% performance loss after padding zeros in previous designs. (3) Performance loss due to static dataflow. Kernel performance in LLM depends on varied input data features, hardware configurations, etc. A single and static dataflow may lead to a 50.25% performance loss for GEMMs of different shapes in LLM inference. We present FlashDecoding++, a fast LLM inference engine supporting mainstream LLMs and hardware back-ends. To tackle the above challenges, FlashDecoding++ creatively proposes: (1) Asynchronized softmax with unified max value. FlashDecoding++ introduces a unified max value technique for different partial softmax computations to avoid synchronization. (2) Flat GEMM optimization with double buffering. FlashDecoding++ points out that flat GEMMs with different shapes face varied bottlenecks. Then, techniques like double buffering are introduced. (3) Heuristic dataflow with hardware resource adaptation. FlashDecoding++ heuristically optimizes dataflow using different hardware resource considering input dynamics. Due to the versatility of optimizations in FlashDecoding++, FlashDecoding++ can achieve up to 4.86x and 2.18x speedup on both NVIDIA and AMD GPUs compared to Hugging Face implementations. FlashDecoding++ also achieves an average speedup of 1.37x compared to state-of-the-art LLM inference engines on mainstream LLMs.

Large language models (LLMs) propel the prosperity of interactive AI applications showcased by ChatGPT that demand timely response of inference services. However, LLM inference is computation intensive and memory intensive, and improper parameter configuration at LLM platforms may exacerbate the inference time. In this paper, we analyze the impact of LLM output token distribution on the inference queueing delay, where the max-token clipping and the batched inference are considered. By formulating an M/G/1 model, we observe that enforcing a maximum output token limit on a very small fraction of inference requests can significantly reduce the queueing delay, and our model facilitates the selection of the optimal limit. For the batch inference, we model the service process as a bulk queue in which the batch processing time is affected by the batch size and the maximum token size inside this batch jointly. The queueing delays of the batching of all buffered requests (dynamic batching), the batching of constant number of requests (fixed batching), and the batching without intra-batch waiting (elastic batching) are derived. Experimental results show that our mathematical models coincide with the event-driven simulations well.

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data production pipeline to process YouTube videos and their closed captions (CC, same as ASR), resulting in Live-CC-5M dataset for pre-training and Live-WhisperX-526K dataset for high-quality supervised fine-tuning (SFT). Remarkably, even without SFT, the ASR-only pre-trained LiveCC-7B-Base model demonstrates competitive general video QA performance and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new LiveSports-3K benchmark, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final LiveCC-7B-Instruct model can surpass advanced 72B models (Qwen2.5-VL-72B-Instruct, LLaVA-Video-72B) in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B/8B scale on popular video QA benchmarks such as VideoMME and OVOBench, demonstrating the broad generalizability of our approach. All resources of this paper have been released at https://showlab.github.io/livecc.

Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting. It is time to unify them into one online LALM: a model that, through an always-on perceive-decide-respond loop, listens to sound, environment, and instructions in real time and reacts on the fly. We formalize this regime as the Audio Interaction Model, and realize it with Audio-Interaction, a unified streaming model that retains offline task execution while adding online general audio instruction following, from dialogue to full voice chatting, deciding when to respond from the semantics of the stream. To enable this, we propose SoundFlow, a framework that instantiates the perceive-decide-respond loop end to end, from data to training to deployment, through streaming-native data construction, comprehension-aware training, and asynchronous low-latency inference for stable real-time interaction. We further construct StreamAudio-2M, a 2.6M-item streaming corpus spanning 7 fundamental abilities and 28 sub-tasks, and Proactive-Sound-Bench for evaluating proactive audio intervention. Across 8 benchmarks, Audio-Interaction preserves competitive performance on mainstream audio tasks while unlocking capabilities inaccessible to offline LALMs, including real-time ASR, streaming audio instruction following, and proactive help.

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM applications demand flexible and high-performance attention solutions. We present FlashInfer: a customizable and efficient attention engine for LLM serving. FlashInfer tackles KV-cache storage heterogeneity using block-sparse format and composable formats to optimize memory access and reduce redundancy. It also offers a customizable attention template, enabling adaptation to various settings through Just-In-Time (JIT) compilation. Additionally, FlashInfer's load-balanced scheduling algorithm adjusts to dynamism of user requests while maintaining compatibility with CUDAGraph which requires static configuration. FlashInfer have been integrated into leading LLM serving frameworks like SGLang, vLLM and MLC-Engine. Comprehensive kernel-level and end-to-end evaluations demonstrate FlashInfer's ability to significantly boost kernel performance across diverse inference scenarios: compared to state-of-the-art LLM serving solutions, FlashInfer achieve 29-69% inter-token-latency reduction compared to compiler backends for LLM serving benchmark, 28-30% latency reduction for long-context inference, and 13-17% speedup for LLM serving with parallel generation.

Web crawl is a main source of large language models' (LLMs) pretraining data, but the majority of crawled web pages are discarded in pretraining due to low data quality. This paper presents Crawl4LLM, an efficient web crawling method that explores the web graph based on the preference of LLM pretraining. Specifically, it leverages the influence of a webpage in LLM pretraining as the priority score of the web crawler's scheduler, replacing the standard graph connectivity based priority. Our experiments on a web graph containing 900 million webpages from a commercial search engine's index demonstrate the efficiency of Crawl4LLM in obtaining high-quality pretraining data. With just 21% URLs crawled, LLMs pretrained on Crawl4LLM data reach the same downstream performances of previous crawls, significantly reducing the crawling waste and alleviating the burdens on websites. Our code is publicly available at https://github.com/cxcscmu/Crawl4LLM.

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where information arrives sequentially. Motivated by the streaming nature of video data, we investigate two streaming reasoning paradigms for LVLMs. The first, an interleaved paradigm, alternates between receiving frames and producing partial reasoning but remains constrained by strictly ordered cache updates. To better match streaming inputs, we propose Think-as-You-See (TaYS), a unified framework enabling true concurrent reasoning. TaYS integrates parallelized CoT generation, stream-constrained training, and stream-parallel inference. It further employs temporally aligned reasoning units, streaming attention masks and positional encodings, and a dual KV-cache that decouples visual encoding from textual reasoning. We evaluate all paradigms on the Qwen2.5-VL family across representative video CoT tasks, including event dynamics analysis, causal reasoning, and thematic understanding. Experiments show that TaYS consistently outperforms both batch and interleaved baselines, improving reasoning performance while substantially reducing time-to-first-token (TTFT) and overall reasoning delay. These results demonstrate the effectiveness of data-aligned streaming reasoning in enabling efficient and responsive video understanding for LVLMs. We release our code at https://github.com/EIT-NLP/StreamingLLM/tree/main/TaYS{this repository.}

Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems often suffer severe head-of-line (HOL) blocking. While prior work explored PCIe-based offloading, these approaches cannot sustain responsiveness under high request rates, often failing to meet tight Time-To-First-Token (TTFT) and Time-Between-Tokens (TBT) SLOs. We present SuperInfer, a high-performance LLM inference system designed for emerging Superchips (e.g., NVIDIA GH200) with tightly coupled GPU-CPU architecture via NVLink-C2C. SuperInfer introduces RotaSched, the first proactive, SLO-aware rotary scheduler that rotates requests to maintain responsiveness on Superchips, and DuplexKV, an optimized rotation engine that enables full-duplex transfer over NVLink-C2C. Evaluations on GH200 using various models and datasets show that SuperInfer improves TTFT SLO attainment rates by up to 74.7% while maintaining comparable TBT and throughput compared to state-of-the-art systems, demonstrating that SLO-aware scheduling and memory co-design unlocks the full potential of Superchips for responsive LLM serving.

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with full attention leads to quadratic computational costs and poor performance on long videos. Meanwhile, simple sliding window methods are also flawed, as they either break coherence or suffer from high latency due to redundant recomputation. In this paper, we introduce StreamingVLM, a model designed for real-time, stable understanding of infinite visual input. Our approach is a unified framework that aligns training with streaming inference. During inference, we maintain a compact KV cache by reusing states of attention sinks, a short window of recent vision tokens, and a long window of recent text tokens. This streaming ability is instilled via a simple supervised fine-tuning (SFT) strategy that applies full attention on short, overlapped video chunks, which effectively mimics the inference-time attention pattern without training on prohibitively long contexts. For evaluation, we build Inf-Streams-Eval, a new benchmark with videos averaging over two hours that requires dense, per-second alignment between frames and text. On Inf-Streams-Eval, StreamingVLM achieves a 66.18% win rate against GPT-4O mini and maintains stable, real-time performance at up to 8 FPS on a single NVIDIA H100. Notably, our SFT strategy also enhances general VQA abilities without any VQA-specific fine-tuning, improving performance on LongVideoBench by +4.30 and OVOBench Realtime by +5.96. Code is available at https://github.com/mit-han-lab/streaming-vlm.

Trading is a highly competitive task that requires a combination of strategy, knowledge, and psychological fortitude. With the recent success of large language models(LLMs), it is appealing to apply the emerging intelligence of LLM agents in this competitive arena and understanding if they can outperform professional traders. In this survey, we provide a comprehensive review of the current research on using LLMs as agents in financial trading. We summarize the common architecture used in the agent, the data inputs, and the performance of LLM trading agents in backtesting as well as the challenges presented in these research. This survey aims to provide insights into the current state of LLM-based financial trading agents and outline future research directions in this field.

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of LLMs, function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting without fine-tuning. This paper proposes a simple yet controllable target-driven approach called Reverse Chain to empower LLMs with capabilities to use external APIs with only prompts. Given that most open-source LLMs have limited tool-use or tool-plan capabilities, LLMs in Reverse Chain are only employed to implement simple tasks, e.g., API selection and argument completion, and a generic rule is employed to implement a controllable multiple functions calling. In this generic rule, after selecting a final API to handle a given task via LLMs, we first ask LLMs to fill the required arguments from user query and context. Some missing arguments could be further completed by letting LLMs select another API based on API description before asking user. This process continues until a given task is completed. Extensive numerical experiments indicate an impressive capability of Reverse Chain on implementing multiple function calling. Interestingly enough, the experiments also reveal that tool-use capabilities of the existing LLMs, e.g., ChatGPT, can be greatly improved via Reverse Chain.

Speech Large Language Models (Speech LLMs) lack a principled mechanism for streaming inference: their label-synchronous generation has no acoustic-frame alignment, making real-time decoding and end-of-utterance detection difficult. We propose TRADE TRansducer-Augmented DEcoder, which augments a multimodal LLM with a transducer branch that shares the audio encoder and uses the LLM's hidden states directly as the prediction network -- coupling frame-synchronous acoustic alignment with the LLM's linguistic reasoning. Three design choices make the system accurate, streamable, and long-form capable: (1)Tightly coupled dual vocabularies -- a compact transducer vocabulary derived from the LLM vocabulary, enabling zero-cost score fusion; (2)Chunk-synchronized streaming training with gradient stopping, eliminating the train-inference mismatch at offline-equivalent memory cost; and (3)Localized Decoder Audio Attention (LDAA), a causal sliding window that caps KV-cache memory independently of utterance length. A single TRADE checkpoint supports offline and streaming decoding across a continuous range of latency operating points. TRADE achieves 6.71% average WER on the Open ASR Leaderboard, while the streaming recognition with 960ms chunk size reaches 8.40% from the same checkpoint. On long-form speech, it obtains 3.64% WER on TED-LIUM and 10.88% on Earnings-22 without external segmentation. TRADE provides sentence-end punctuation timestamps that, when combined with acoustic voice activity detection (VAD), improve end-of-utterance detection by +0.03 F_1 over acoustic VAD alone.

Large language models (LLMs) under-perform on low-resource languages due to limited training data. We present a method to efficiently collect text data for low-resource languages from the entire Common Crawl corpus. Our approach, UnifiedCrawl, filters and extracts common crawl using minimal compute resources, yielding mono-lingual datasets much larger than previously available sources. We demonstrate that leveraging this data to fine-tuning multilingual LLMs via efficient adapter methods (QLoRA) significantly boosts performance on the low-resource language, while minimizing VRAM usage. Our experiments show large improvements in language modeling perplexity and an increase in few-shot prompting scores. Our work and released source code provide an affordable approach to improve LLMs for low-resource languages using consumer hardware. Our source code is available here at https://github.com/bethelmelesse/unifiedcrawl.

We introduce ProVideLLM, an end-to-end framework for real-time procedural video understanding. ProVideLLM integrates a multimodal cache configured to store two types of tokens - verbalized text tokens, which provide compressed textual summaries of long-term observations, and visual tokens, encoded with DETR-QFormer to capture fine-grained details from short-term observations. This design reduces token count by 22x over existing methods in representing one hour of long-term observations while effectively encoding fine-granularity of the present. By interleaving these tokens in our multimodal cache, ProVideLLM ensures sub-linear scaling of memory and compute with video length, enabling per-frame streaming inference at 10 FPS and streaming dialogue at 25 FPS, with a minimal 2GB GPU memory footprint. ProVideLLM also sets new state-of-the-art results on six procedural tasks across four datasets.

Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text. However, efficiently serving LMMs in production environments poses significant challenges due to their complex architectures and heterogeneous characteristics across their multi-stage inference pipelines. We present the first comprehensive systems analysis of two prominent LMM architectures, decoder-only and cross-attention, across six representative open-source models, revealing key systems design implications. We also present an in-depth analysis of production LMM inference traces, uncovering unique workload characteristics, including variable, heavy-tailed request distributions and bursty traffic patterns. Based on these insights, we propose ModServe, a modular LMM serving system that decouples stages for independent optimization and adaptive scaling. ModServe dynamically reconfigures stages and handles bursty traffic with modality-aware scheduling and autoscaling to meet tail latency SLOs while minimizing costs. ModServe achieves 3.3-5.5x higher throughput (leading to 25-41.3% cost saving) while meeting SLOs on a 128-GPU cluster with production traces.

Large language models (LLMs) use function calls to interface with external tools and data source. However, the current approach to LLM function calling is inherently synchronous, where each call blocks LLM inference, limiting LLM operation and concurrent function execution. In this work, we propose AsyncLM, a system for asynchronous LLM function calling. AsyncLM improves LLM's operational efficiency by enabling LLMs to generate and execute function calls concurrently. Instead of waiting for each call's completion, AsyncLM introduces an interrupt mechanism to asynchronously notify the LLM in-flight when function calls return. We design an in-context protocol for function calls and interrupts, provide fine-tuning strategy to adapt LLMs to the interrupt semantics, and implement these mechanisms efficiently on LLM inference process. We demonstrate that AsyncLM can reduce end-to-end task completion latency from 1.6x-5.4x compared to synchronous function calling on a set of benchmark tasks in the Berkeley function calling leaderboard (BFCL). Furthermore, we discuss how interrupt mechanisms can be extended to enable novel human-LLM or LLM-LLM interactions.

Serving systems for Large Language Models (LLMs) are often optimized to improve quality of service (QoS) and throughput. However, due to the lack of open-source LLM serving workloads, these systems are frequently evaluated under unrealistic workload assumptions. Consequently, performance may degrade when systems are deployed in real-world scenarios. This work presents BurstGPT, an LLM serving workload with 10.31 million traces from regional Azure OpenAI GPT services over 213 days. BurstGPT captures LLM serving characteristics from user, model and system perspectives: (1) User request concurrency: burstiness variations of requests in Azure OpenAI GPT services, revealing diversified concurrency patterns in different services and model types. (2) User conversation patterns: counts and intervals within conversations for service optimizations. (3) Model response lengths: auto-regressive serving processes of GPT models, showing statistical relations between requests and their responses. (4) System response failures: failures of conversation and API services, showing intensive resource needs and limited availability of LLM services in Azure. The details of the characteristics can serve multiple purposes in LLM serving optimizations, such as system evaluation and trace provisioning. In our demo evaluation with BurstGPT, frequent variations in BurstGPT reveal declines in efficiency, stability, or reliability in realistic LLM serving. We identify that the generalization of KV cache management, scheduling and disaggregation optimizations can be improved under realistic workload evaluations. BurstGPT is publicly available now at https://github.com/HPMLL/BurstGPT and is widely used to develop prototypes of LLM serving frameworks in the industry.

Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video streams difficult. Existing streaming methods typically use an interleaved perception-generation paradigm, which prevents concurrent perception and generation and leads to early memory decay as streams grow, hurting long-range dependency modeling. We propose Think While Watching, a memory-anchored streaming video reasoning framework that preserves continuous segment-level memory during multi-turn interaction. We build a three-stage, multi-round chain-of-thought dataset and adopt a stage-matched training strategy, while enforcing strict causality through a segment-level streaming causal mask and streaming positional encoding. During inference, we introduce an efficient pipeline that overlaps watching and thinking and adaptively selects the best attention backend. Under both single-round and multi-round streaming input protocols, our method achieves strong results. Built on Qwen3-VL, it improves single-round accuracy by 2.6% on StreamingBench and by 3.79% on OVO-Bench. In the multi-round setting, it maintains performance while reducing output tokens by 56%. Code is available at: https://github.com/wl666hhh/Think_While_Watching/

Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges such as frequent hardware failures, intricate parallelization strategies, and imbalanced resource utilization. In this paper, we present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme. Specifically, we investigate discrepancies between LLMs and prior task-specific Deep Learning (DL) workloads, explore resource utilization patterns, and identify the impact of various job failures. Our analysis summarizes hurdles we encountered and uncovers potential opportunities to optimize systems tailored for LLMs. Furthermore, we introduce our system efforts: (1) fault-tolerant pretraining, which enhances fault tolerance through LLM-involved failure diagnosis and automatic recovery. (2) decoupled scheduling for evaluation, which achieves timely performance feedback via trial decomposition and scheduling optimization.