GitHub · Python
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU, Tenstorrent, Huawei Ascent NPU, and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
- Stars
- 1,294
- Forks
- 222
- Stars gained in 24 hours
- +1
- Forks gained in 24 hours
- +4
Topics: cuda, gptq, metal, mlx, npu, optimum, peft, quantization, rocm, sglang
Latest data point: Nov 21, 2026 · 1,294 stars · 222 forks