quark-torch-ptq
Torch LLM PTQ workflow for AMD Quark — for PyTorch / HuggingFace transformers models (safetensors input). Use when the user wants a complete PTQ pipeline: model inspection, quantization planning, script generation, and optional execution. Stops at the quantized output. Trigger for "quantize my model", "run PTQ", "run model quantization", "full quantization pipeline", "quantize Llama/Qwen/Mistral with FP8/INT4", or any request that spans more than one PTQ step. For a run that also validates and evaluates accuracy use quark-torch-llm-ptq-eval. Not for .onnx input models — use quark-onnx-ptq instead.
Source facts
- Repository
- amd/Quark
- Last source activity
- July 9, 2026 at 06:10
- Detected SKILL.md language
- English
- Stars
- 166
- Forks
- 30
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
