Intel Neural Compressor GitHub README

Fields

id

sources/qlab2-neural-compressor-readme

URL

https://github.com/intel/neural-compressor

Publisher

Intel

Kind

repo

Accessed

2026-10-03

notes

Verified coverage: static/dynamic quantization, SmoothQuant, weight-only, QAT, mixed precision; INT8/FP8/MXFP8/INT4/MXFP4/NVFP4 + sparsity; frameworks PyTorch/TensorFlow/JAX; low-bit LLM/VLM integration is via AutoRound; hardware targets Gaudi, Core Ultra, Xeon, Xeon CPU Max, Data Center GPU Flex/Max with extensive testing, AMD CPU / ARM CPU / NVIDIA GPU limited. Confirms Neural Compressor's advanced low-bit path is AutoRound, not its own implementation. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Notes

Verified coverage: static/dynamic quantization, SmoothQuant, weight-only, QAT, mixed precision; INT8/FP8/MXFP8/INT4/MXFP4/NVFP4 + sparsity; frameworks PyTorch/TensorFlow/JAX; low-bit LLM/VLM integration is via AutoRound; hardware targets Gaudi, Core Ultra, Xeon, Xeon CPU Max, Data Center GPU Flex/Max with extensive testing, AMD CPU / ARM CPU / NVIDIA GPU limited. Confirms Neural Compressor's advanced low-bit path is AutoRound, not its own implementation. | SOURCE AUDIT 2026-10-03: the 'published' field held a verbatim copy of this notes paragraph instead of a date (field corruption across the qlab2-* batch); published set to null because a GitHub README, doc page or source header has no reliable publication date of its own. Content of the document itself was re-verified live 2026-10-03 and the notes are correct.

Cross-references

This record references no other records.