Add deepspeed test to amd scheduled CI (#27633)

* add deepspeed scheduled test for amd

* fix image

* add dockerfile

* add comment

* enable tests

* trigger

* remove trigger for this branch

* trigger

* change runner env to trigger the docker build image test

* use new docker image

* remove test suffix from docker image tag

* replace test docker image with original image

* push new image

* Trigger

* add back amd tests

* fix typo

* add amd tests back

* fix

* comment until docker image build scheduled test fix

* remove deprecated deepspeed build option

* upgrade torch

* update docker & make tests pass

* Update docker/transformers-pytorch-deepspeed-amd-gpu/Dockerfile

* fix

* tmp disable test

* precompile deepspeed to avoid timeout during tests

* fix comment

* trigger deepspeed tests with new image

* comment tests

* trigger

* add sklearn dependency to fix slow tests

* enable back other tests

* final update

---------

Co-authored-by: Felix Marty <felix@hf.co>
Co-authored-by: Félix Marty <9808326+fxmarty@users.noreply.github.com>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

docker/transformers-pytorch-amd-gpu/Dockerfile

@@ -22,7 +22,11 @@ RUN python3 -m pip install --no-cache-dir --upgrade pip setuptools ninja git+htt
 
 ARG REF=main
 WORKDIR /
+
+# Invalidate docker cache from here if new commit is available.
+ADD https://api.github.com/repos/huggingface/transformers/git/refs/heads/main version.json
 RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+
 RUN python3 -m pip install --no-cache-dir -e ./transformers[dev-torch,testing,video]
 
 RUN python3 -m pip uninstall -y tensorflow flax

docker/transformers-pytorch-deepspeed-amd-gpu/Dockerfile

@@ -0,0 +1,45 @@
+FROM rocm/dev-ubuntu-22.04:5.6
+LABEL maintainer="Hugging Face"
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG PYTORCH='2.1.1'
+ARG TORCH_VISION='0.16.1'
+ARG TORCH_AUDIO='2.1.1'
+ARG ROCM='5.6'
+
+RUN apt update && \
+    apt install -y --no-install-recommends \
+    libaio-dev \
+    git \
+    # These are required to build deepspeed.
+    python3-dev \
+    python-is-python3 \
+    rocrand-dev \
+    rocthrust-dev \
+    hipsparse-dev \
+    hipblas-dev \
+    rocblas-dev && \
+    apt clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN python3 -m pip install --no-cache-dir --upgrade pip ninja "pydantic<2"
+RUN python3 -m pip uninstall -y apex torch torchvision torchaudio
+RUN python3 -m pip install torch==$PYTORCH torchvision==$TORCH_VISION torchaudio==$TORCH_AUDIO --index-url https://download.pytorch.org/whl/rocm$ROCM --no-cache-dir
+
+# Pre-build DeepSpeed, so it's be ready for testing (to avoid timeout)
+RUN DS_BUILD_CPU_ADAM=1 DS_BUILD_FUSED_ADAM=1 python3 -m pip install deepspeed --global-option="build_ext" --global-option="-j8" --no-cache-dir -v --disable-pip-version-check 2>&1
+
+ARG REF=main
+WORKDIR /
+
+# Invalidate docker cache from here if new commit is available.
+ADD https://api.github.com/repos/huggingface/transformers/git/refs/heads/main version.json
+RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
+
+RUN python3 -m pip install --no-cache-dir ./transformers[accelerate,testing,sentencepiece,sklearn]
+
+# When installing in editable mode, `transformers` is not recognized as a package.
+# this line must be added in order for python to be aware of transformers.
+RUN cd transformers && python3 setup.py develop
+
+RUN python3 -c "from deepspeed.launcher.runner import main"

docker/transformers-pytorch-deepspeed-latest-gpu/Dockerfile

@@ -34,7 +34,7 @@ RUN python3 -m pip uninstall -y torch-tensorrt
 
 # recompile apex
 RUN python3 -m pip uninstall -y apex
-RUN git clone https://github.com/NVIDIA/apex
+# RUN git clone https://github.com/NVIDIA/apex
 #  `MAX_JOBS=1` disables parallel building to avoid cpu memory OOM when building image on GitHub Action (standard) runners
 # TODO: check if there is alternative way to install latest apex
 # RUN cd apex && MAX_JOBS=1 python3 -m pip install --global-option="--cpp_ext" --global-option="--cuda_ext" --no-cache -v --disable-pip-version-check .
@@ -44,7 +44,7 @@ RUN python3 -m pip uninstall -y deepspeed
 # This has to be run (again) inside the GPU VMs running the tests.
 # The installation works here, but some tests fail, if we don't pre-build deepspeed again in the VMs running the tests.
 # TODO: Find out why test fail.
-RUN DS_BUILD_CPU_ADAM=1 DS_BUILD_FUSED_ADAM=1 DS_BUILD_UTILS=1 python3 -m pip install deepspeed --global-option="build_ext" --global-option="-j8" --no-cache -v --disable-pip-version-check 2>&1
+RUN DS_BUILD_CPU_ADAM=1 DS_BUILD_FUSED_ADAM=1 python3 -m pip install deepspeed --global-option="build_ext" --global-option="-j8" --no-cache -v --disable-pip-version-check 2>&1
 
 # When installing in editable mode, `transformers` is not recognized as a package.
 # this line must be added in order for python to be aware of transformers.