serving-llms-on-instinct
Serves AI models on AMD Instinct GPU hardware using vLLM. Use this skill whenever the user wants to run, serve, deploy, start, host, or launch a language model on an AMD GPU, AMD Instinct, MI300X, MI325X, MI350X, or MI355X. Also use when the user mentions vLLM on ROCm, vLLM on AMD, serving on HBM, or asks how to get a model running on AMD data center hardware. Use when the user asks "run Qwen3", "serve DeepSeek", "start a vLLM endpoint", "get a model running on my AMD machine", or any similar phrasing. Handles the full flow: GPU detection, environment validation, vLLM configuration, launch, and health verification. Do not use for NVIDIA GPUs, consumer AMD GPUs (RX series, Radeon), Ryzen AI, NPU, MI250X, or MI100.
Pinned to revision 4e8964e24a5a, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Bash
- Read
Files
- skills/serving-llms-on-instinct/SKILL.md
- skills/serving-llms-on-instinct/LICENSE
- skills/serving-llms-on-instinct/data/blacklist.json
- skills/serving-llms-on-instinct/data/gpu_overrides.json
- skills/serving-llms-on-instinct/data/recipes_cache.json
- skills/serving-llms-on-instinct/evals/evals.json
- skills/serving-llms-on-instinct/evals/hooks.py
- skills/serving-llms-on-instinct/evals/machine.yml
- skills/serving-llms-on-instinct/reference.md
- skills/serving-llms-on-instinct/scripts/detect.py
- skills/serving-llms-on-instinct/scripts/estimate_vram.py
- skills/serving-llms-on-instinct/scripts/sync_recipes.py
- skills/serving-llms-on-instinct/scripts/validate.py
- skills/serving-llms-on-instinct/skill-card.md
Every link opens the file at its source, pinned to the revision this page describes.