search

huggingface / optimum-benchmark

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
Apache License 2.0
255 stars 48 forks source link

Build from source quantization packages #239

Closed baptistecolle closed 2 months ago

baptistecolle commented 3 months ago

Related to: https://github.com/huggingface/optimum-benchmark/issues/226

This PR build the AutoAWQ and AUTOGPTQ from source to fix the above mentioned issue.

IlyasMoutawwakil commented 3 months ago

thanks for the addition ! it's really cool to have quant libs compiled with the latest torch, and anyone will be able to use these optimized images.