Recompile apex in DeepSpeed CI image (#20788)

Recompile apex in DeepSpeed CI image

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
This commit is contained in:
Yih-Dar 2022-12-15 21:35:27 +01:00 committed by GitHub
parent 491e951875
commit 1543cee7c8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -24,6 +24,11 @@ RUN python3 -m pip install --no-cache-dir ./transformers[deepspeed-testing]
RUN python3 -m pip install torch-tensorrt==1.3.0 --find-links https://github.com/pytorch/TensorRT/releases/expanded_assets/v1.3.0 RUN python3 -m pip install torch-tensorrt==1.3.0 --find-links https://github.com/pytorch/TensorRT/releases/expanded_assets/v1.3.0
# recompile apex
RUN python3 -m pip uninstall -y apex
RUN git clone https://github.com/NVIDIA/apex
RUN cd apex && python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
# Pre-build **latest** DeepSpeed, so it would be ready for testing (otherwise, the 1st deepspeed test will timeout) # Pre-build **latest** DeepSpeed, so it would be ready for testing (otherwise, the 1st deepspeed test will timeout)
RUN python3 -m pip uninstall -y deepspeed RUN python3 -m pip uninstall -y deepspeed
# This has to be run (again) inside the GPU VMs running the tests. # This has to be run (again) inside the GPU VMs running the tests.