lablab-ai-amd-developer-hackathon (Lablab.ai AMD Developer Hackathon)

posted an update 1 day ago

Post

3322

First stuntd model is on the Hub :)

pollix/stuntd-support-triage is three small heads on the Laya encoder that triage a support ticket in one request: category, urgency and needs_human. About 50 MB each, all three answers come back at a p50 of 71ms through the daemon.

On 1,000 tickets they never saw, each head answers on its own when it's sure: category 99.9%, needs_human 92%, urgency 76%. A ticket only skips the big model when all three are sure, that's 72.7% of them, and all three are right on 97.1% of those.

It's the support demo from the repo, so the tickets are generated and the teacher is a rule. The point is to show what a head looks like and how fast it is, then you train the same thing on your own traffic with your own LLM as the teacher.

hf download pollix/stuntd-support-triage --local-dir support-heads

Model: pollix/stuntd-support-triage
Everything in one place: pollix/stuntd-6abe0a33303828e10c72ab41
Code: https://github.com/bladedevoff/stuntd

3 replies

·

pollix

posted an update 2 days ago

Post

6339

stuntd 0.1.2 is out 🎉

stuntd sits in front of your LLM, learns its typed decisions and answers the confident ones locally with a small head on the Laya encoder by @convaiinnovations . About 20ms on GPU and 60ms on CPU, and anything it isn't sure about still goes to the big model.

New in 0.1.2:
- decisions with several fields, like category + urgency + needs_human in one call, answered locally only when every field is sure
- the Anthropic Messages API learns too, not only OpenAI
- auto_retrain: the daemon retrains a site in the background once enough new traffic comes in, so collect, train, shadow and live run on their own
- serve --lazy loads the checkpoint on the first request

Try it in the browser: pollix/stuntd
Code: https://github.com/bladedevoff/stuntd

pip install -U stuntd

1 reply

·

pollix

posted an update 9 days ago

Post

948

Built a Space for stuntd: pollix/stuntd

For each question it shows the same answer twice: zero-shot Laya, and a small head trained on the frozen Laya encoder. You get the option probabilities, the confidence threshold and the latency. When the head isn't sure, it hands the question back to the teacher instead of guessing.

On jevbench, same machine, n=500: agnews 86.0 → 92.6, banking77 38.2 → 69.6. Everything runs locally; heads train in 4-20 minutes on a laptop GPU.

Code (Apache-2.0): https://github.com/bladedevoff/stuntd

Rurouni-II

in lablab-ai-amd-developer-hackathon/dr-rocm 2 months ago

Gradio SDK version update

1

#1 opened 2 months ago by

Rurouni-II

jeffboudier

posted an update 3 months ago

Post

585

@alvarobartt published a step-by-step guide to deploy zai-org/GLM-5.2 on AMD GPUs, using newly released features in Microsoft Foundry. The FP8 model fits on a single node of MI300X GPUs, which cuts the bill in half vs. H100.

https://alvarobartt.com/goal-glm-5.2-on-foundry/

Achoyyy

in lablab-ai-amd-developer-hackathon/warehouseeye 4 months ago

Update README.md

#1 opened 4 months ago by

Achoyyy

Yatsuiii

in lablab-ai-amd-developer-hackathon/asd-interpreter-merged 5 months ago

Add model card: architecture, training, usage, limitations

#1 opened 5 months ago by

Yatsuiii

msradam

in lablab-ai-amd-developer-hackathon/riprap-nyc 5 months ago

fix: conditional Ollama timeout — 5s when vLLM primary, 240s otherwise

#3 opened 5 months ago by

msradam

fix: cold-start, keepalives, vLLM readiness probe, fast Ollama fallback timeout

#2 opened 5 months ago by

msradam

fix: cold-start timeouts, keepalives, vLLM probe, fast-Ollama-fallback

#1 opened 5 months ago by

msradam

pollix

posted an update 5 months ago

Post

161

Shipped StudioMI300 for the AMD x lablab hackathon. One English sentence becomes a 30-second cinematic reel, end-to-end on a single AMD Instinct MI300X.

Every model in the pipeline is Apache 2.0 or MIT.

🎬 Director Agent — Qwen3.5-35B-A3B via vLLM with AITER MoE acceleration. Plans 6 shots, character bibles, music brief, per-shot voice-over.

🎨 Character keyframes — FLUX.2 klein 4B reference editing. No LoRA training step. Identity stays consistent across shots by construction.

🎞️ Animation — Wan2.2-I2V-A14B with ParaAttention FBCache (lossless 2x) and selective torch.compile on transformer_2 (another 1.2x). End-to-end Wan2.2 inference went from 25.9 min to 10.4 min per 720p clip.

🔍 Vision Critic — same Qwen3.5 checkpoint reloaded with a 10-label failure taxonomy (character drift, extras invade frame, camera ignored, walking backwards, hand artifact, wardrobe drift, neon glow leak, stylized AI look, random intimacy, object morphing). Bad clips auto-retry with targeted strategies. Up to 3 attempts.

🎵 Music — ACE-Step v1 generates 30s instrumental from Director's brief.

🗣️ Narration — Kokoro-82M, 9 languages. Director picks language to match setting. Tokyo to Japanese, Paris to French, Mumbai to Hindi.

The 192 GB HBM3 on MI300X is what lets four very different model architectures share one card sequentially. On a 24 GB consumer GPU this stack needs 4-5 separate machines wired together.

Space (live infra restoring after hackathon close, pls like this space):
lablab-ai-amd-developer-hackathon/studiomi300

Code (Apache 2.0):
https://github.com/bladedevoff/studiomi300

Special thanks to the FLUX, Wan2.2, ACE-Step and Kokoro teams for keeping serious generative AI open. The pipeline composes their work into something none of them alone can produce — a complete cinematic artifact from a single prompt.

#AMDHackathon #ROCm #MI300X #OpenSource