intel / intel/neural-compressor
[Feature] support MXFP W4A8 evaluation on benchmark/vllm-qdq-plugin for accuracy simulation purpose.
Open
- Dominant language
- Python
- Stars
- 2.7k
- Forks
- 322
- Avg merge
- 4d 9h
- Merged PRs (30d)
- 25
Description
This issue has no description.
Contributor guide
Assessment
This issue has not been assessed yet.