SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[Awq] Enable the possibility to skip quantization for some target modules (#27950)

Browse Source 
* v1

* add docstring

* add tests

* add awq 0.1.8

* oops

* fix test
This commit is contained in:
Younes Belkada
2023-12-25 11:06:56 +01:00
committed by GitHub
parent 29e7a1e183
commit fa21ead73d
4 changed files with 42 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docker/transformers-all-latest-gpu/Dockerfile
View File

@@ -56,7 +56,7 @@ RUN python3 -m pip install --no-cache-dir auto-gptq --extra-index-url https://hu
RUN python3 -m pip install --no-cache-dir einops
# Add autoawq for quantization testing
RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.7/autoawq-0.1.7+cu118-cp38-cp38-linux_x86_64.whl
RUN python3 -m pip install --no-cache-dir https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.8/autoawq-0.1.8+cu118-cp38-cp38-linux_x86_64.whl
# For bettertransformer + gptq
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/optimum@main#egg=optimum