[ROCm] add support to ROCm 6.0 and MI300 (#2274)

This commit is contained in:
Hongxia Yang
2024-01-26 15:41:10 -05:00
committed by GitHub
parent 5265631d15
commit 6b7de1a030
8 changed files with 96 additions and 13 deletions

View File

@@ -1,4 +1,24 @@
FROM rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1
# default base image
ARG BASE_IMAGE="rocm/pytorch:rocm6.0_ubuntu20.04_py3.9_pytorch_2.1.1"
FROM $BASE_IMAGE
ARG BASE_IMAGE="rocm/pytorch:rocm6.0_ubuntu20.04_py3.9_pytorch_2.1.1"
RUN echo "Base image is $BASE_IMAGE"
# BASE_IMAGE for ROCm_5.7: "rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1"
# BASE_IMAGE for ROCm_6.0: "rocm/pytorch:rocm6.0_ubuntu20.04_py3.9_pytorch_2.1.1"
# this does not always work for all rocm versions
RUN LLVM_GFX_ARCH=$(/opt/rocm/llvm/bin/amdgpu-offload-arch) && \
echo "LLVM_GFX_ARCH is $LLVM_GFX_ARCH"
ARG FA_GFX_ARCHS="gfx90a;gfx942"
RUN echo "FA_GFX_ARCHS is $FA_GFX_ARCHS"
ARG FA_BRANCH="3d2b6f5"
RUN echo "FA_BRANCH is $FA_BRANCH"
# Install some basic utilities
RUN apt-get update && apt-get install python3 python3-pip -y
@@ -37,17 +57,23 @@ RUN mkdir libs \
&& cd libs \
&& git clone https://github.com/ROCmSoftwarePlatform/flash-attention.git \
&& cd flash-attention \
&& git checkout 3d2b6f5 \
&& git checkout ${FA_BRANCH} \
&& git submodule update --init \
&& export GPU_ARCHS=$(/opt/rocm/llvm/bin/amdgpu-offload-arch) \
&& patch /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/utils/hipify/hipify_python.py hipify_patch.patch \
&& export GPU_ARCHS=${FA_GFX_ARCHS} \
&& if [ "$BASE_IMAGE" = "rocm/pytorch:rocm5.7_ubuntu22.04_py3.10_pytorch_2.0.1" ]; then \
patch /opt/conda/envs/py_3.10/lib/python3.10/site-packages/torch/utils/hipify/hipify_python.py hipify_patch.patch; fi \
&& python3 setup.py install \
&& cd ..
COPY ./ /app/vllm
RUN python3 -m pip install --upgrade pip
RUN pip install xformers==0.0.23 --no-deps
RUN python3 -m pip install xformers==0.0.23 --no-deps
# Error related to odd state for numpy 1.20.3 where there is no METADATA etc, but an extra LICENSES_bundled.txt.
# Manually removed it so that later steps of numpy upgrade can continue
RUN if [ "$BASE_IMAGE" = "rocm/pytorch:rocm6.0_ubuntu20.04_py3.9_pytorch_2.1.1" ]; then \
rm -rf /opt/conda/envs/py_3.9/lib/python3.9/site-packages/numpy-1.20.3.dist-info/; fi
RUN cd /app \
&& cd vllm \