saymrwulf/transformers
1
0
Fork 0
mirror of https://github.com/saymrwulf/transformers.git synced 2026-05-14 20:58:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix docker CI : install autogptq from source (#35000)

Browse source 
* Fixed Docker

* Test ci

* Finally

* add comment
This commit is contained in:
Mohamed Mekkouri 2024-11-28 16:31:36 +01:00 committed by GitHub
parent 01ad80f820
commit f491096f7d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
docker/transformers-quantization-latest-gpu/Dockerfile
View file

@ -36,8 +36,10 @@ RUN python3 -m pip install --no-cache-dir einops
# Add bitsandbytes for mixed int8 testing
RUN python3 -m pip install --no-cache-dir bitsandbytes
# Add auto-gptq for gtpq quantization testing
RUN python3 -m pip install --no-cache-dir auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/
# Add auto-gptq for gtpq quantization testing, installed from source for pytorch==2.5.1 compatibility
# TORCH_CUDA_ARCH_LIST="7.5+PTX" is added to make the package compile for Tesla T4 gpus available for the CI.
RUN pip install gekko
RUN git clone https://github.com/PanQiWei/AutoGPTQ.git && cd AutoGPTQ && TORCH_CUDA_ARCH_LIST="7.5+PTX" python3 setup.py install
# Add optimum for gptq quantization testing
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/optimum@main#egg=optimum