intel/neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

↗ Open on GitHub

Stars

2,706

Forks

322

Language

Python

License

Apache-2.0

Last push

5 days ago

Python large-language-models quantization knowledge-distillation sparsity pruning post-training-quantization awq smoothquant int4 quantization-aware-training gptq fp4 auto-tuning int8 low-precision mxformat sparsegpt

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.

Related intel (0)

No related intel yet