Buckets:
| run_id,engine,model,source,component,bytes,kind,scope | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,weights_reported,31632434135,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,kv_pool_reported,37430639985,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,other_device_memory_residual,4741996216,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,weights,31412968448,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,requested_kv,1019215872,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,overhead,5480658737,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,weights_reported,24835648389,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,kv_pool_reported,45333379810,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,other_device_memory_residual,5357803929,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,weights_reported,2147483648,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,kv_pool_reported,68010807132,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,other_device_memory_residual,4322062500,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,weights_reported,8922794557,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,kv_pool_reported,61246233640,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,other_device_memory_residual,4732852635,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,weights_reported,16449724744,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,kv_pool_reported,35970351104,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,other_device_memory_residual,21577932472,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,weights_reported,14012330803,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,kv_pool_reported,24953759990,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,other_device_memory_residual,35105317847,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,weights,13761264768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,requested_kv,1211498496,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,overhead,6349153636,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,17126182093,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,49907519980,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,3640320327,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16127602196,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,54052163420,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,3835019920,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,weights_reported,2523293286,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,kv_pool_reported,67645734912,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,other_device_memory_residual,3153697178,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,weights,2471628800,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,requested_kv,1073741824,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,overhead,5432137214,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,16213501542,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,48339856916,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,3100765062,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,weights_reported,14516989460,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,kv_pool_reported,55662776156,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,other_device_memory_residual,3734356624,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,weights,14496047104,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,overhead,4661020260,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,48092896297,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,18940805776,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,2797265223,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,27681064222,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,26622673552,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,weights_reported,9524089979,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,kv_pool_reported,55018531062,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,other_device_memory_residual,2822095503,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,weights,11148920768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,overhead,6495759205,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16857746637,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,46407121634,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,3114186833,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,16943645983,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,53644141528,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,2061752073,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,weights_reported,1267015352,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,kv_pool_reported,68891275428,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,other_device_memory_residual,3126685860,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,weights,1503264768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,overhead,5474281111,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61224758804,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,8912057140,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,3693420216,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,weights_reported,65541200937,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,kv_pool_reported,4617089844,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,other_device_memory_residual,4930236579,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,weights,65524246528,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,requested_kv,8589934592,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,overhead,6628119396,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,weights_reported,16406775071,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,kv_pool_reported,53772990546,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,other_device_memory_residual,3965043343,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,weights,16381470720,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,overhead,6129804951,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,weights_reported,9255654523,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,30193620090,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,30480258827,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,62341450301,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,2899102924,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,3023841527,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17738214932,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,47523813130,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,3174333154,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-a100-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,weights_reported,31643171553,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,kv_pool_reported,102198746808,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,other_device_memory_residual,3467011687,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,weights,31412968448,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,requested_kv,1019215872,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-dsv2-lite/default,sglang,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,overhead,5480658737,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,weights_reported,24835648389,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,kv_pool_reported,110058536960,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,runtime,other_device_memory_residual,4029551739,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-12b/default,sglang,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,weights_reported,2147483648,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,kv_pool_reported,132735964282,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,runtime,other_device_memory_residual,3008490374,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-1b/default,sglang,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,weights_reported,8922794557,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,kv_pool_reported,125971390792,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,runtime,other_device_memory_residual,3282965627,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma3-4b/default,sglang,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,runtime,weights_reported,64005750129,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,runtime,kv_pool_reported,52570399704,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,runtime,other_device_memory_residual,10007944887,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,hf-mem,weights,62546177752,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,hf-mem,requested_kv,16958095360,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-31b/default,sglang,google/gemma-4-31B-it,hf-mem,overhead,8029191882,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,weights_reported,16449724744,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,kv_pool_reported,79070347920,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,runtime,other_device_memory_residual,43183463464,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gemma4-e4b/default,sglang,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,weights_reported,18865643848,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,kv_pool_reported,51561082388,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,runtime,other_device_memory_residual,67144347812,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,weights,13761264768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,requested_kv,1211498496,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-gpt-oss-20b/default,sglang,openai/gpt-oss-20b,hf-mem,overhead,6349153636,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,17126182093,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,111475876168,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,3141030379,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-internvl35-8b/default,sglang,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16127602196,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,118755845734,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,3165776774,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama31-8b/default,sglang,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,weights_reported,2523293286,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,kv_pool_reported,132370892062,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,runtime,other_device_memory_residual,2637042812,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,weights,2471628800,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,requested_kv,1073741824,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llama32-1b/default,sglang,meta-llama/Llama-3.2-1B-Instruct,hf-mem,overhead,5432137214,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,16213501542,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,107610405602,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,2466586296,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-llava-ov-7b/default,sglang,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,weights_reported,14516989460,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,kv_pool_reported,120366458470,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,runtime,other_device_memory_residual,3065113478,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,weights,14496047104,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-7b/default,sglang,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,overhead,4661020260,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,48092896297,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,80509161964,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,2597868011,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-mistral-small31/default,sglang,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,61675730370,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,57239163372,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-nemotron-9b/default,sglang,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,weights_reported,9524089979,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,kv_pool_reported,114289079746,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,runtime,other_device_memory_residual,2265511363,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,weights,11148920768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-phi4mm/default,sglang,microsoft/Phi-4-multimodal-instruct,hf-mem,overhead,6495759205,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16857746637,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,104496554312,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,2614645227,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen25vl-7b/default,sglang,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,16943645983,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,118455198024,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,1434032537,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen2audio-7b-ml8k/default,sglang,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,weights_reported,1267015352,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,kv_pool_reported,133616432578,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,runtime,other_device_memory_residual,2297555846,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,weights,1503264768,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-06b/default,sglang,Qwen/Qwen3-0.6B,hf-mem,overhead,5474281111,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61224758804,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,73637214290,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,3115948442,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-30b/default,sglang,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,weights_reported,65541200937,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,kv_pool_reported,69342246994,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,runtime,other_device_memory_residual,4264684421,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,weights,65524246528,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,requested_kv,8589934592,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-32b/default,sglang,Qwen/Qwen3-32B,hf-mem,overhead,6628119396,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,weights_reported,16406775071,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,kv_pool_reported,118476672860,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,runtime,other_device_memory_residual,3161582469,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,weights,16381470720,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3-8b/default,sglang,Qwen/Qwen3-8B,hf-mem,overhead,6129804951,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,weights_reported,9255654523,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,62534723830,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,59654914703,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen35-4b/default,sglang,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,runtime,weights_reported,70319352054,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,runtime,kv_pool_reported,28583007354,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,runtime,other_device_memory_residual,29791470224,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,hf-mem,weights,71903645408,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,hf-mem,requested_kv,821821440,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen36-35b/default,sglang,Qwen/Qwen3.6-35B-A3B,hf-mem,overhead,9020433815,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,62341450301,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,60408715018,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,4712636089,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-30b/default,sglang,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17738214932,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,105033425224,engine_reported,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,4636635300,derived_residual,device_0_ready_cache_pool | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/sglang-h200-qwen3vl-8b/default,sglang,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,weights_reported,31482110280,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,kv_pool_reported,44860933407,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,other_device_memory_residual,2267650457,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,weights,31412968448,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,requested_kv,1019215872,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,overhead,5480658737,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,weights_reported,25136296100,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,51174535332,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,1714757304,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,weights_reported,24288040059,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,51002736640,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,1692527493,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,weights_reported,2104533975,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,kv_pool_reported,70824010711,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,other_device_memory_residual,2412689490,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,weights_reported,2104533975,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,kv_pool_reported,74571369677,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,other_device_memory_residual,1379045212,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,weights_reported,9244917105,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,kv_pool_reported,67226975601,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,other_device_memory_residual,1553696030,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,weights_reported,8396661064,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,kv_pool_reported,67763846513,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,other_device_memory_residual,1454039367,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,weights_reported,16181289288,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,kv_pool_reported,60193966653,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,other_device_memory_residual,1809716347,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,weights_reported,15214921646,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,kv_pool_reported,56446607688,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,other_device_memory_residual,1804850954,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,weights_reported,14817637171,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,kv_pool_reported,61299920732,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,other_device_memory_residual,1798978929,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,weights,13761264768,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,requested_kv,1211498496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,overhead,6349153636,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,17072495002,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,57101590200,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,1385252782,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,16396037652,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,59947006034,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,1344903578,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16106127360,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,59130962248,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,1834294968,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16106127360,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,60451664691,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,1297927373,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,weights_reported,2491081032,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,kv_pool_reported,74786118042,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,other_device_memory_residual,1044088094,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,weights,2471628800,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,requested_kv,1073741824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,overhead,5432137214,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,16181289288,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,60805999493,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,1315124019,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,15343770665,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,61181809132,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,1273516523,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,weights_reported,14506252042,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,kv_pool_reported,62942745723,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,other_device_memory_residual,1188959355,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,weights,14496047104,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,overhead,4661020260,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,48060684042,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,28808493138,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,1510830244,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,47180215747,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,28915867320,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,1478617989,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,57348550820,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,1756616458,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,58604828754,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,1267896156,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,weights_reported,18017387807,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,kv_pool_reported,58841051955,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,other_device_memory_residual,1481721774,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,weights,22362553472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,weights_reported,15375982920,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,kv_pool_reported,61160334295,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,other_device_memory_residual,1285847777,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,weights,22362553472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16825534382,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,51604032061,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1425518101,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,15461882266,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,61074434949,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1283750625,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml64k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16825534382,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,58443767480,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1380555162,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,469762048,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,15461882266,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,61074434949,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1264876257,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,469762048,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b-ml8k/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16825534382,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,56167434813,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1381477909,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,15461882266,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,61074434949,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,1283750625,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,16804059546,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,60118804726,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,1408908656,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,15515569357,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,60805999493,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,1290880942,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,weights_reported,1202590843,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,kv_pool_reported,75924284375,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,other_device_memory_residual,1272006574,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,weights,1503264768,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,overhead,5474281111,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,12970801234,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,2926323958,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,15558519030,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,1840166994,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,weights_reported,65530463519,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,kv_pool_reported,10114647982,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,other_device_memory_residual,1770206003,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,weights,65524246528,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,requested_kv,8589934592,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,overhead,6628119396,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,weights_reported,16396037652,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,kv_pool_reported,59947006034,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,other_device_memory_residual,1344903578,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,weights,16381470720,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,overhead,6129804951,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,weights_reported,9191230013,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,64156073984,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,3849909699,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,weights_reported,8525510083,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,65283502899,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,3822311178,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,62255550956,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,12981538652,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,1842683576,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,15558519030,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,1840166994,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17706002678,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,57498874675,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1386259415,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,19327352832,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,16481936998,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,59861106688,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1344903578,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,19327352832,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml128k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17706002678,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,57498874675,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1365287895,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,1207959552,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,16481936998,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,59861106688,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1323932058,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,1207959552,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-ml8k/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17856326533,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,56317758669,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,2052147118,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17706002678,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,57498874675,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1384162263,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,16481936998,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,59861106688,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1342806426,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,weights_reported,3650722202,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,kv_pool_reported,73927124582,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,other_device_memory_residual,1062207488,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,hf-mem,weights,8987139520,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-a100-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,weights_reported,3092376453,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,kv_pool_reported,74496207749,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-a100-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,other_device_memory_residual,1118578934,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-a100-whisper-v3/default,vllm,openai/whisper-large-v3,hf-mem,weights,3086981120,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,weights_reported,31482110280,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,kv_pool_reported,102402757755,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,runtime,other_device_memory_residual,3171355197,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,weights,31412968448,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,requested_kv,1019215872,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-dsv2-lite/default,vllm,deepseek-ai/DeepSeek-V2-Lite-Chat,hf-mem,overhead,5480658737,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,runtime,weights_reported,25136296100,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,106955423089,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,2657636843,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/default,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,runtime,weights_reported,24288040059,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,107352707564,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,2940836249,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b-ml8k/text-only,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,weights_reported,25136296100,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,106955423089,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,2846380523,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/default,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,weights_reported,24288040059,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,kv_pool_reported,107352707564,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,runtime,other_device_memory_residual,3024722329,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,weights,24374650080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,requested_kv,7856979968,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-12b/text-only,vllm,google/gemma-3-12b-it,hf-mem,overhead,7687559652,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,weights_reported,2104533975,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,kv_pool_reported,134260677673,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,runtime,other_device_memory_residual,1578106880,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b-swap/default,vllm,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,weights_reported,2104533975,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,kv_pool_reported,130470369034,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,runtime,other_device_memory_residual,2610660639,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,weights,1999771904,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,requested_kv,515211264,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-1b/default,vllm,google/gemma-3-1b-it,hf-mem,overhead,6983169739,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,weights_reported,9244917105,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,kv_pool_reported,123297773650,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,runtime,other_device_memory_residual,2718370365,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/default,vllm,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,weights_reported,8396661064,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,kv_pool_reported,123823907144,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,runtime,other_device_memory_residual,2738503024,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,weights,8600158944,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,requested_kv,2740781056,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma3-4b/text-only,vllm,google/gemma-3-4b-it,hf-mem,overhead,7371933156,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,runtime,weights_reported,63340030198,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,runtime,kv_pool_reported,68601365135,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,runtime,other_device_memory_residual,3128824955,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,hf-mem,weights,62546177752,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,hf-mem,requested_kv,16958095360,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/default,vllm,google/gemma-4-31B-it,hf-mem,overhead,8029191882,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,runtime,weights_reported,62180389028,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,runtime,kv_pool_reported,70007966925,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,runtime,other_device_memory_residual,2911224463,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,hf-mem,weights,62546177752,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,hf-mem,requested_kv,16958095360,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-31b/text-only,vllm,google/gemma-4-31B-it,hf-mem,overhead,8029191882,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,weights_reported,16320875725,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,kv_pool_reported,116050016338,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,runtime,other_device_memory_residual,2711911137,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/default,vllm,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,weights_reported,15343770665,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,kv_pool_reported,115105123533,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,runtime,other_device_memory_residual,2681460490,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,weights,15992314836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,requested_kv,2151776256,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gemma4-e4b/text-only,vllm,google/gemma-4-E4B-it,hf-mem,overhead,7317102180,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,weights_reported,13990855967,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,kv_pool_reported,119249766973,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,runtime,other_device_memory_residual,3159191716,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,weights,13761264768,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,requested_kv,1211498496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-gpt-oss-20b/default,vllm,openai/gpt-oss-20b,hf-mem,overhead,6349153636,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,17072495002,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,114707839058,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,2383916564,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/default,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,weights_reported,16396037652,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,kv_pool_reported,117682103910,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,runtime,other_device_memory_residual,2283924358,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,weights,17056636928,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-internvl35-8b/text-only,vllm,OpenGVLab/InternVL3_5-8B,hf-mem,overhead,6456960663,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16106127360,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,119861799813,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,1555960955,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b-swap/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,weights_reported,16106127360,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,kv_pool_reported,118422985769,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,runtime,other_device_memory_residual,2164302807,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,weights,16060522496,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama31-8b/default,vllm,meta-llama/Llama-3.1-8B-Instruct,hf-mem,overhead,5873908836,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,weights_reported,2491081032,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,kv_pool_reported,132510478500,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,runtime,other_device_memory_residual,1844948500,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,weights,2471628800,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,requested_kv,1073741824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llama32-1b/default,vllm,meta-llama/Llama-3.2-1B-Instruct,hf-mem,overhead,5432137214,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,16181289288,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,117649891656,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,2281323888,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/default,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,weights_reported,15343770665,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,kv_pool_reported,118831007662,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,runtime,other_device_memory_residual,2210356265,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,weights,16061615168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-llava-ov-7b/text-only,vllm,llava-hf/llava-onevision-qwen2-7b-ov-hf,hf-mem,overhead,6404739479,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,weights_reported,14506252042,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,kv_pool_reported,121461675131,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,runtime,other_device_memory_residual,1761481851,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,weights,14496047104,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-7b/default,vllm,mistralai/Mistral-7B-Instruct-v0.3,hf-mem,overhead,4661020260,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,48060684042,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,86114094285,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,2438945833,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/default,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,weights_reported,47180215747,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,kv_pool_reported,87155623854,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,runtime,other_device_memory_residual,2319827599,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,weights,48022722560,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,requested_kv,5368709120,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-mistral-small31/text-only,vllm,mistralai/Mistral-Small-3.1-24B-Instruct-2503,hf-mem,overhead,6900397668,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,118025701294,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,1592786944,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b-swap/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,weights_reported,17802639442,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,kv_pool_reported,116458038231,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,runtime,other_device_memory_residual,2210440151,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,weights,17776454656,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,requested_kv,988807168,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-nemotron-9b/default,vllm,nvidia/NVIDIA-Nemotron-Nano-9B-v2,hf-mem,overhead,6468596478,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,weights_reported,18017387807,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,kv_pool_reported,115674206700,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,runtime,other_device_memory_residual,2508990709,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,weights,22362553472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/default,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,weights_reported,15375982920,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,kv_pool_reported,118820270244,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,runtime,other_device_memory_residual,2199367188,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,weights,22362553472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25omni-7b/text-only,vllm,Qwen/Qwen2.5-Omni-7B,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,16825534382,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,114697101640,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,2364790538,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/default,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,weights_reported,15461882266,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,kv_pool_reported,118723633480,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,runtime,other_device_memory_residual,2208007454,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,weights,16584333312,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,requested_kv,1879048192,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen25vl-7b/text-only,vllm,Qwen/Qwen2.5-VL-7B-Instruct,hf-mem,overhead,8227124631,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,16804059546,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,116715736269,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,2424936857,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/default,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,weights_reported,15515569357,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,kv_pool_reported,118508885115,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,runtime,other_device_memory_residual,2247433912,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,weights,16794189824,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,requested_kv,4294967296,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen2audio-7b-ml8k/text-only,vllm,Qwen/Qwen2-Audio-7B-Instruct,hf-mem,overhead,6193233764,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,weights_reported,1202590843,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,kv_pool_reported,133262097777,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,runtime,other_device_memory_residual,2071440916,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,weights,1503264768,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,requested_kv,3758096384,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-06b/default,vllm,Qwen/Qwen3-0.6B,hf-mem,overhead,5474281111,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,75226352189,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,1857279755,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b-swap/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,kv_pool_reported,72123238318,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,runtime,other_device_memory_residual,2966002074,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,weights,61064245248,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-30b/default,vllm,Qwen/Qwen3-30B-A3B-Instruct-2507,hf-mem,overhead,6349540606,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,weights_reported,65530463519,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,kv_pool_reported,67162551091,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,runtime,other_device_memory_residual,2922465198,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,weights,65524246528,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,requested_kv,8589934592,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-32b/default,vllm,Qwen/Qwen3-32B,hf-mem,overhead,6628119396,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,weights_reported,16396037652,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,kv_pool_reported,117682103910,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,runtime,other_device_memory_residual,2283924358,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,weights,16381470720,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3-8b/default,vllm,Qwen/Qwen3-8B,hf-mem,overhead,6129804951,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,weights_reported,9191230013,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,122921964012,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,2753602519,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/default,vllm,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,weights_reported,8525510083,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,kv_pool_reported,123705795543,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,runtime,other_device_memory_residual,2719376998,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,weights,9319737856,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,requested_kv,1193803776,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen35-4b/text-only,vllm,Qwen/Qwen3.5-4B,hf-mem,overhead,8927133080,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,runtime,weights_reported,70276402381,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,runtime,kv_pool_reported,61052960113,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,runtime,other_device_memory_residual,3784897986,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,weights,71903645408,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,requested_kv,821821440,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/default,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,overhead,9020433815,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,runtime,weights_reported,69374459249,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,runtime,kv_pool_reported,62073014845,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,runtime,other_device_memory_residual,3733895250,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,weights,71903645408,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,requested_kv,821821440,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen36-35b/text-only,vllm,Qwen/Qwen3.6-35B-A3B,hf-mem,overhead,9020433815,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,62330712883,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,70609262346,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,3008951747,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/default,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,weights_reported,61128122040,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,kv_pool_reported,72123238318,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,runtime,other_device_memory_residual,2966002074,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,weights,62141508064,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,requested_kv,3221225472,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-30b/text-only,vllm,Qwen/Qwen3-VL-30B-A3B-Instruct,hf-mem,overhead,7432509899,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17706002678,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,116909009797,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,1623321477,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b-swap/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,17856326533,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,115362821571,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,2373263032,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/default,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,weights_reported,16481936998,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,kv_pool_reported,117585467146,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,runtime,other_device_memory_residual,2296758928,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,weights,17534247392,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-qwen3vl-8b/text-only,vllm,Qwen/Qwen3-VL-8B-Instruct,hf-mem,overhead,7862052503,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,weights_reported,3650722202,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,kv_pool_reported,132725226865,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,runtime,other_device_memory_residual,1596729589,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-smolvlm2-ml8k/text-only,vllm,HuggingFaceTB/SmolVLM2-2.2B-Instruct,hf-mem,weights,8987139520,estimated,batch_1_requested_context_all_weights | |
| mm/vllm-h200-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,weights_reported,3092376453,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,kv_pool_reported,133305047450,engine_reported,device_0_ready_cache_pool | |
| mm/vllm-h200-whisper-v3/default,vllm,openai/whisper-large-v3,runtime,other_device_memory_residual,1652849377,derived_residual,device_0_ready_cache_pool | |
| mm/vllm-h200-whisper-v3/default,vllm,openai/whisper-large-v3,hf-mem,weights,3086981120,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,runtime,weights_reported,7294293115,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,runtime,kv_pool_reported,2650800128,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,runtime,recurrent_state_reported,0,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,runtime,other_device_memory_residual,1646914437,derived_residual,device_0_ready_cache_pool | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,hf-mem,weights,8148401472,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,hf-mem,requested_kv,2650800128,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-gemma3-12b-q4km,llama.cpp,unsloth/gemma-3-12b-it-GGUF,hf-mem,overhead,792650054,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,runtime,weights_reported,1091378872,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,runtime,kv_pool_reported,410517504,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,runtime,recurrent_state_reported,639631,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,runtime,other_device_memory_residual,601956025,derived_residual,device_0_ready_cache_pool | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,hf-mem,weights,1091380480,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,hf-mem,requested_kv,411156480,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-lfm3-17b-q4km,llama.cpp,LiquidAI/LFM3-1.7B-GGUF,hf-mem,overhead,665719930,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,runtime,weights_reported,4671762596,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,runtime,kv_pool_reported,4831838208,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,runtime,recurrent_state_reported,0,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,runtime,other_device_memory_residual,645566300,derived_residual,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,hf-mem,weights,4671766528,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,hf-mem,requested_kv,4831838208,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen3-8b-q4km,llama.cpp,unsloth/Qwen3-8B-GGUF,hf-mem,overhead,665719930,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,runtime,weights_reported,15387276083,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,runtime,kv_pool_reported,2147483648,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,runtime,recurrent_state_reported,156887941,engine_reported,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,runtime,other_device_memory_residual,1880023368,derived_residual,device_0_ready_cache_pool | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,hf-mem,weights,16665869248,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,hf-mem,requested_kv,2304376832,estimated,batch_1_requested_context_all_weights | |
| startup/llamacpp-v-qwen38-27b-q4km,llama.cpp,unsloth/Qwen3.8-27B-GGUF,hf-mem,overhead,1173440429,estimated,batch_1_requested_context_all_weights | |
Xet Storage Details
- Size:
- 133 kB
- Xet hash:
- f634acefcbd96735554df9e0e62bbddee1f597391183ed9038db0aced3bdfc0f
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.