mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 13:43:50 +08:00
[Hardware] feat: Support AMD (ROCMm Kernel) - Update Dockerfile/Docker Image (#2390)
### What does this PR do? > Update Dockerfile/Docker Image ### Checklist Before Starting - [X] Search for similar PRs. - [X] Format the PR title (This will be checked by the CI) ### Test > Done ### API and Usage Example > Usage example(s) [AMD_toturial](https://github.com/volcengine/verl/blob/main/docs/amd_tutorial/amd_build_dockerfile_page.rst). ### Design & Code Changes > Dockerfile/Docker Image dependency: ROCm: 6.3.4 (patch version) Pytoch: 2.7.0 vllm: >=0.8.5 sglang: >=v0.4.6.post4 megatron-lm: TransformerEngine==1.14.0, megatron-core==0.12.0 Ray: >=2.45 Also allow VLM training ### Checklist Before Submitting > [!IMPORTANT] > Please check all the following items before requesting a review, otherwise the reviewer might deprioritize this PR for review. - [X] Read the [Contribute Guide](https://github.com/volcengine/verl/blob/main/docs/amd_tutorial/amd_build_dockerfile_page.rst). - [X] Apply [pre-commit checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting): `pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always` - [X] Add / Update [the documentation](https://github.com/volcengine/verl/tree/main/docs). - [X] Add unit or end-to-end test(s) to [the CI workflow](https://github.com/volcengine/verl/tree/main/.github/workflows) to cover all the code. If not feasible, explain why: ... - [X] Once your PR is ready for CI, send a message in [the `ci-request` channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the `verl` Slack workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
This commit is contained in:
Ethan (Yusheng) Su
committed by
GitHub
GitHub
parent
b5e711eab5
commit
526098d664
@ -1,36 +1,294 @@
|
||||
# Build the docker in the repo dir:
|
||||
# docker build -f docker/Dockerfile.rocm -t verl-rocm:03.04.2015 .
|
||||
# docker images # you can find your built docker
|
||||
# FROM "compute-artifactory.amd.com:5000/rocm-plus-docker/framework/compute-rocm-rel-6.4:94_ubuntu22.04_py3.10_pytorch_release-2.7_575e247"
|
||||
FROM "rlfoundation.azurecr.io/rocm6.3.4:vllm-0.8.5-numa-patch-ubuntu-22.04"
|
||||
|
||||
SHELL ["/bin/bash", "-ceuxo", "pipefail"]
|
||||
|
||||
ENV MAX_JOBS=512
|
||||
|
||||
ENV PATH="/usr/local/python3.12/bin:$PATH"
|
||||
RUN ln -sf /usr/bin/python3.12 /usr/bin/python && \
|
||||
ln -sf /usr/bin/pip3.12 /usr/bin/pip
|
||||
|
||||
############################################
|
||||
############################################
|
||||
RUN apt-get update
|
||||
RUN apt-get install -y pkg-config liblzma-dev
|
||||
############################################
|
||||
############################################
|
||||
|
||||
|
||||
# Support - Traing: fsdp; Inference: vllm
|
||||
# FROM rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
# Support - Traing: fsdp; Inference: vllm, sglang
|
||||
FROM lmsysorg/sglang:v0.4.6.post5-rocm630
|
||||
###########################################
|
||||
##########Install TransformerEngine########
|
||||
###########################################
|
||||
WORKDIR /workspace/
|
||||
# transformer-engine install
|
||||
# https://github.com/ROCm/TransformerEngine
|
||||
|
||||
# Set working directory
|
||||
# WORKDIR $PWD/app
|
||||
RUN rm -rf TransformerEngine
|
||||
RUN git clone --recursive https://github.com/ROCm/TransformerEngine.git
|
||||
WORKDIR /workspace/TransformerEngine
|
||||
RUN git checkout 236178e5
|
||||
# git checkout bb061ade
|
||||
# git checkout 864405c
|
||||
|
||||
ENV NVTE_FRAMEWORK=pytorch
|
||||
ENV NVTE_ROCM_ARCH=gfx942
|
||||
ENV NVTE_USE_HIPBLASLT=1
|
||||
ENV NVTE_USE_ROCM=1
|
||||
|
||||
# export CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr:${CMAKE_PREFIX_PATH:-}"
|
||||
ENV CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr"
|
||||
|
||||
|
||||
# ENV NVTE_BUILD_MAX_JOBS=$(MAX_JOBS)
|
||||
|
||||
RUN MAX_JOBS=$(MAX_JOBS) pip install . -vvv
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
####################################################################################
|
||||
################Install vllm - sglang require vllm 0.6.7 dependency#################
|
||||
####################################################################################
|
||||
#### Require vllm 0.6.7 - checkout 113274a0
|
||||
WORKDIR /workspace/
|
||||
RUN rm -rf vllm
|
||||
RUN pip uninstall -y vllm
|
||||
# Refer to here (down-grade vllm to 0.6.3): https://docs.vllm.ai/en/v0.6.3/getting_started/amd-installation.html
|
||||
RUN git clone https://github.com/ROCm/vllm.git
|
||||
# git clone https://github.com/vllm-project/vllm.git
|
||||
WORKDIR /workspace/vllm
|
||||
RUN git checkout 113274a0
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
#ENV MAX_JOBS=512
|
||||
ENV MAX_JOBS=${MAX_JOBS}
|
||||
RUN pip install "boto3>=1.26.0"
|
||||
RUN pip install setuptools_scm
|
||||
# will add src into py. You can delete the repo
|
||||
RUN python3 setup.py install
|
||||
WORKDIR /workspace/
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############For hack docker################
|
||||
###########################################
|
||||
RUN pip install setuptools==75.8.0
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############build sgalng###################
|
||||
###########################################
|
||||
# Set environment variables
|
||||
ENV BASE_DIR=/sgl-workspace
|
||||
ENV BUILD_TYPE=all
|
||||
ENV SGL_REPO=https://github.com/sgl-project/sglang
|
||||
ENV SGL_BRANCH=v0.4.6.post5
|
||||
ENV TRITON_REPO=https://github.com/ROCm/triton.git
|
||||
ENV TRITON_COMMIT=improve_fa_decode_3.0.0
|
||||
ENV AITER_REPO=https://github.com/ROCm/aiter.git
|
||||
ENV AITER_COMMIT=v0.1.2
|
||||
# v0.1.2 version - commit id: 9d11f47
|
||||
# ENV AITER_COMMIT=9d11f47
|
||||
|
||||
ENV HIP_FORCE_DEV_KERNARG=1
|
||||
ENV HSA_NO_SCRATCH_RECLAIM=1
|
||||
ENV SGLANG_SET_CPU_AFFINITY=1
|
||||
ENV SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
|
||||
ENV NCCL_MIN_NCHANNELS=112
|
||||
ENV MOE_PADDING=1
|
||||
ENV VLLM_FP8_PADDING=1
|
||||
ENV VLLM_FP8_ACT_PADDING=1
|
||||
ENV VLLM_FP8_WEIGHT_PADDING=1
|
||||
ENV VLLM_FP8_REDUCE_CONV=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
ENV AMDGPU_TARGETS=gfx942
|
||||
ENV ROCM_ARCH=gfx942
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
|
||||
# Switch to working directory
|
||||
WORKDIR /sgl-workspace
|
||||
|
||||
# Clean and create directory
|
||||
RUN rm -rf /sgl-workspace && mkdir -p /sgl-workspace
|
||||
|
||||
# Clone and build sglang
|
||||
RUN git clone ${SGL_REPO} \
|
||||
&& cd sglang \
|
||||
&& git checkout ${SGL_BRANCH} || echo "Using default branch" \
|
||||
&& cd sgl-kernel \
|
||||
&& rm -f pyproject.toml \
|
||||
&& mv pyproject_rocm.toml pyproject.toml \
|
||||
&& python setup_rocm.py install \
|
||||
&& cd .. \
|
||||
&& if [ "$BUILD_TYPE" = "srt" ]; then \
|
||||
python -m pip --no-cache-dir install -e "python[srt_hip]"; \
|
||||
else \
|
||||
python -m pip --no-cache-dir install -e "python[all_hip]"; \
|
||||
fi \
|
||||
&& cd /sgl-workspace \
|
||||
&& cp -r /sgl-workspace/sglang /sglang \
|
||||
&& python -m pip cache purge
|
||||
|
||||
# Install common Python packages
|
||||
RUN pip install IPython orjson python-multipart torchao pybind11
|
||||
|
||||
# Rebuild Triton
|
||||
RUN pip uninstall -y triton || true \
|
||||
&& git clone ${TRITON_REPO} \
|
||||
&& cd triton \
|
||||
&& git checkout ${TRITON_COMMIT} \
|
||||
&& cd python \
|
||||
&& python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
|
||||
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942 --amdgpu-lower-module-lds-strategy=1"
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
|
||||
# Build aiter
|
||||
#version: Commit 9d11f47
|
||||
# && git checkout ${AITER_COMMIT} \
|
||||
RUN pip uninstall -y aiter || true
|
||||
RUN git clone ${AITER_REPO} \
|
||||
&& cd aiter \
|
||||
&& git checkout ${AITER_COMMIT} \
|
||||
&& git submodule sync \
|
||||
&& git submodule update --init --recursive \
|
||||
&& PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
# && PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py develop \
|
||||
# && PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py develop \
|
||||
|
||||
# Copy MI300X config
|
||||
RUN find /sgl-workspace/sglang/python/sglang/srt/layers/quantization/configs/ \
|
||||
/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs/ \
|
||||
-type f -name '*MI300X*' | \
|
||||
xargs -I {} sh -c 'vf_config=$(echo "$1" | sed "s/MI300X/MI300X_VF/"); cp "$1" "$vf_config"' -- {}
|
||||
|
||||
# Environment setup complete.
|
||||
RUN echo "Environment setup complete."
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
###############vllm v0.8.5#################
|
||||
###########################################
|
||||
# ENV GITHUB_USERNAME=yushengsu-thu
|
||||
# ENV GITHUB_MAIL=yushengsu@gmail.com
|
||||
|
||||
# RUN git config --global user.name "${GITHUB_USERNAME}" \
|
||||
# && git config --global user.email "${GITHUB_MAIL}"
|
||||
|
||||
WORKDIR /workspace/
|
||||
|
||||
ENV VLLM_TARGET_DEVICE=rocm
|
||||
ENV ROCM_PATH=/opt/rocm
|
||||
ENV SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev
|
||||
|
||||
# Find the repo path in: DockerFile/Dockerfile.rocm_yang
|
||||
# RUN git clone https://github.com/RLFoundation/vllm-patch.git
|
||||
RUN pip uninstall -y vllm || true
|
||||
RUN rm -rf vllm-patch
|
||||
RUN git clone https://github.com/RLFoundation/vllm-patch.git \
|
||||
&& cd vllm-patch \
|
||||
&& git checkout v0.8.5-sleep-numa \
|
||||
&& rm -rf build/ dist/ *.egg-info \
|
||||
&& ln -sf /opt/rocm/lib/libamdhip64.so /usr/lib/libamdhip64.so \
|
||||
&& SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py install
|
||||
# RUN SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py develop
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#########################################
|
||||
#### Install megatron-core###############
|
||||
#########################################
|
||||
RUN pip uninstall -y megatron-core && \
|
||||
git clone https://github.com/yushengsu-thu/Megatron-LM-amd_version.git && \
|
||||
cd Megatron-LM-amd_version && \
|
||||
pip install -vvv -e . && \
|
||||
cd /workspace/
|
||||
#########################################
|
||||
#########################################
|
||||
#########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#######################################
|
||||
################apex###################
|
||||
#######################################
|
||||
WORKDIR /workspace/
|
||||
RUN pip uninstall -y apex && \
|
||||
git clone https://github.com/ROCm/apex.git && \
|
||||
cd apex && \
|
||||
python setup.py install && \
|
||||
cd /workspace/
|
||||
#######################################
|
||||
#######################################
|
||||
#######################################
|
||||
|
||||
|
||||
|
||||
|
||||
################################################################################
|
||||
###########################Add torch_memory_saver###############################
|
||||
################################################################################
|
||||
# Set environment variables
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--amdgpu-target=gfx90a;gfx942 -D__HIP_PLATFORM_AMD__"
|
||||
ENV CFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
ENV CXXFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
RUN pip install "git+https://github.com/YangWang92/torch_memory_saver_numa.git@numa"
|
||||
################################################################################
|
||||
################################################################################
|
||||
################################################################################
|
||||
|
||||
# Install vllm
|
||||
RUN pip uninstall -y vllm && \
|
||||
rm -rf vllm && \
|
||||
git clone -b v0.6.3 https://github.com/vllm-project/vllm.git && \
|
||||
cd vllm && \
|
||||
MAX_JOBS=$(nproc) python3 setup.py install && \
|
||||
cd .. && \
|
||||
rm -rf vllm
|
||||
|
||||
# Copy the entire project directory
|
||||
COPY . .
|
||||
|
||||
# Install dependencies
|
||||
########################################
|
||||
######Install ray#######################
|
||||
########################################
|
||||
# need to add this patch: https://github.com/ray-project/ray/pull/53531/files
|
||||
RUN pip uninstall ray -y
|
||||
RUN pip install "ray[data,train,tune,serve]>=2.47.0"
|
||||
########################################
|
||||
########################################
|
||||
########################################
|
||||
|
||||
|
||||
|
||||
##########################################
|
||||
#######Install other dependencies#########
|
||||
##########################################
|
||||
RUN pip install "tensordict==0.6.2" --no-deps && \
|
||||
pip install accelerate \
|
||||
codetiming \
|
||||
@ -43,14 +301,21 @@ RUN pip install "tensordict==0.6.2" --no-deps && \
|
||||
peft \
|
||||
"pyarrow>=15.0.0" \
|
||||
pylatexenc \
|
||||
"ray[data,train,tune,serve]<2.45.0" \
|
||||
torchdata \
|
||||
transformers \
|
||||
wandb \
|
||||
orjson \
|
||||
pybind11 && \
|
||||
pip install -e . --no-deps && \
|
||||
python setup.py bdist_wheel
|
||||
pybind11
|
||||
|
||||
# Install torch_memory_saver
|
||||
RUN pip install git+https://github.com/ExtremeViscent/torch_memory_saver.git --no-deps
|
||||
WORKDIR /workspace/
|
||||
RUN git clone https://github.com/volcengine/verl.git && \
|
||||
cd verl && \
|
||||
pip install -e .
|
||||
##########################################
|
||||
##########################################
|
||||
##########################################
|
||||
|
||||
|
||||
|
||||
WORKDIR /workspace/
|
||||
|
||||
CMD ["/usr/bin/bash"]
|
||||
|
||||
58
docker/Dockerfile.rocm_verl-0.3.0.post1
Normal file
58
docker/Dockerfile.rocm_verl-0.3.0.post1
Normal file
@ -0,0 +1,58 @@
|
||||
# Build the docker in the repo dir:
|
||||
# docker build -f docker/Dockerfile.rocm -t verl-rocm:03.04.2015 .
|
||||
# docker images # you can find your built docker
|
||||
|
||||
|
||||
# Support - Traing: fsdp; Inference: vllm
|
||||
# FROM rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
# Support - Traing: fsdp; Inference: vllm, sglang
|
||||
FROM lmsysorg/sglang:v0.4.6.post5-rocm630
|
||||
|
||||
# Set working directory
|
||||
# WORKDIR $PWD/app
|
||||
|
||||
# Set environment variables
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--amdgpu-target=gfx90a;gfx942 -D__HIP_PLATFORM_AMD__"
|
||||
ENV CFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
ENV CXXFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
|
||||
# Install vllm
|
||||
RUN pip uninstall -y vllm && \
|
||||
rm -rf vllm && \
|
||||
git clone -b v0.6.3 https://github.com/vllm-project/vllm.git && \
|
||||
cd vllm && \
|
||||
MAX_JOBS=$(nproc) python3 setup.py install && \
|
||||
cd .. && \
|
||||
rm -rf vllm
|
||||
|
||||
# Copy the entire project directory
|
||||
COPY . .
|
||||
|
||||
# Install dependencies
|
||||
RUN pip install "tensordict==0.6.2" --no-deps && \
|
||||
pip install accelerate \
|
||||
codetiming \
|
||||
datasets \
|
||||
dill \
|
||||
hydra-core \
|
||||
liger-kernel \
|
||||
numpy \
|
||||
pandas \
|
||||
peft \
|
||||
"pyarrow>=15.0.0" \
|
||||
pylatexenc \
|
||||
"ray[data,train,tune,serve]<2.45.0" \
|
||||
torchdata \
|
||||
transformers \
|
||||
wandb \
|
||||
orjson \
|
||||
pybind11
|
||||
|
||||
RUN git clone https://github.com/volcengine/verl.git && \
|
||||
cd verl && \
|
||||
pip install -e .
|
||||
|
||||
# Install torch_memory_saver
|
||||
RUN pip install git+https://github.com/ExtremeViscent/torch_memory_saver.git --no-deps
|
||||
322
docker/Dockerfile.rocm_verl-0.4.1
Normal file
322
docker/Dockerfile.rocm_verl-0.4.1
Normal file
@ -0,0 +1,322 @@
|
||||
# FROM "compute-artifactory.amd.com:5000/rocm-plus-docker/framework/compute-rocm-rel-6.4:94_ubuntu22.04_py3.10_pytorch_release-2.7_575e247"
|
||||
FROM "rlfoundation.azurecr.io/rocm6.3.4:vllm-0.8.5-numa-patch-ubuntu-22.04"
|
||||
|
||||
SHELL ["/bin/bash", "-ceuxo", "pipefail"]
|
||||
|
||||
ENV MAX_JOBS=512
|
||||
|
||||
ENV PATH="/usr/local/python3.12/bin:$PATH"
|
||||
RUN ln -sf /usr/bin/python3.12 /usr/bin/python && \
|
||||
ln -sf /usr/bin/pip3.12 /usr/bin/pip
|
||||
|
||||
############################################
|
||||
############################################
|
||||
RUN apt-get update
|
||||
RUN apt-get install -y pkg-config liblzma-dev
|
||||
############################################
|
||||
############################################
|
||||
|
||||
|
||||
###########################################
|
||||
##########Install TransformerEngine########
|
||||
###########################################
|
||||
WORKDIR /workspace/
|
||||
# transformer-engine install
|
||||
# https://github.com/ROCm/TransformerEngine
|
||||
|
||||
RUN rm -rf TransformerEngine
|
||||
RUN git clone --recursive https://github.com/ROCm/TransformerEngine.git
|
||||
WORKDIR /workspace/TransformerEngine
|
||||
RUN git checkout 236178e5
|
||||
# git checkout bb061ade
|
||||
# git checkout 864405c
|
||||
|
||||
ENV NVTE_FRAMEWORK=pytorch
|
||||
ENV NVTE_ROCM_ARCH=gfx942
|
||||
ENV NVTE_USE_HIPBLASLT=1
|
||||
ENV NVTE_USE_ROCM=1
|
||||
|
||||
# export CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr:${CMAKE_PREFIX_PATH:-}"
|
||||
ENV CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr"
|
||||
|
||||
|
||||
# ENV NVTE_BUILD_MAX_JOBS=$(MAX_JOBS)
|
||||
|
||||
RUN MAX_JOBS=$(MAX_JOBS) pip install . -vvv
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
####################################################################################
|
||||
################Install vllm - sglang require vllm 0.6.7 dependency#################
|
||||
####################################################################################
|
||||
#### Require vllm 0.6.7 - checkout 113274a0
|
||||
WORKDIR /workspace/
|
||||
RUN rm -rf vllm
|
||||
RUN pip uninstall -y vllm
|
||||
# Refer to here (down-grade vllm to 0.6.3): https://docs.vllm.ai/en/v0.6.3/getting_started/amd-installation.html
|
||||
RUN git clone https://github.com/ROCm/vllm.git
|
||||
# git clone https://github.com/vllm-project/vllm.git
|
||||
WORKDIR /workspace/vllm
|
||||
RUN git checkout 113274a0
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
#ENV MAX_JOBS=512
|
||||
ENV MAX_JOBS=${MAX_JOBS}
|
||||
RUN pip install "boto3>=1.26.0"
|
||||
RUN pip install setuptools_scm
|
||||
# will add src into py. You can delete the repo
|
||||
RUN python3 setup.py install
|
||||
WORKDIR /workspace/
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############For hack docker################
|
||||
###########################################
|
||||
RUN pip install setuptools==75.8.0
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############build sgalng###################
|
||||
###########################################
|
||||
# Set environment variables
|
||||
ENV BASE_DIR=/sgl-workspace
|
||||
ENV BUILD_TYPE=all
|
||||
ENV SGL_REPO=https://github.com/sgl-project/sglang
|
||||
ENV SGL_BRANCH=v0.4.6.post5
|
||||
ENV TRITON_REPO=https://github.com/ROCm/triton.git
|
||||
ENV TRITON_COMMIT=improve_fa_decode_3.0.0
|
||||
ENV AITER_REPO=https://github.com/ROCm/aiter.git
|
||||
ENV AITER_COMMIT=v0.1.2
|
||||
# v0.1.2 version - commit id: 9d11f47
|
||||
# ENV AITER_COMMIT=9d11f47
|
||||
|
||||
ENV HIP_FORCE_DEV_KERNARG=1
|
||||
ENV HSA_NO_SCRATCH_RECLAIM=1
|
||||
ENV SGLANG_SET_CPU_AFFINITY=1
|
||||
ENV SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
|
||||
ENV NCCL_MIN_NCHANNELS=112
|
||||
ENV MOE_PADDING=1
|
||||
ENV VLLM_FP8_PADDING=1
|
||||
ENV VLLM_FP8_ACT_PADDING=1
|
||||
ENV VLLM_FP8_WEIGHT_PADDING=1
|
||||
ENV VLLM_FP8_REDUCE_CONV=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
ENV AMDGPU_TARGETS=gfx942
|
||||
ENV ROCM_ARCH=gfx942
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
|
||||
# Switch to working directory
|
||||
WORKDIR /sgl-workspace
|
||||
|
||||
# Clean and create directory
|
||||
RUN rm -rf /sgl-workspace && mkdir -p /sgl-workspace
|
||||
|
||||
# Clone and build sglang
|
||||
RUN git clone ${SGL_REPO} \
|
||||
&& cd sglang \
|
||||
&& git checkout ${SGL_BRANCH} || echo "Using default branch" \
|
||||
&& cd sgl-kernel \
|
||||
&& rm -f pyproject.toml \
|
||||
&& mv pyproject_rocm.toml pyproject.toml \
|
||||
&& python setup_rocm.py install \
|
||||
&& cd .. \
|
||||
&& if [ "$BUILD_TYPE" = "srt" ]; then \
|
||||
python -m pip --no-cache-dir install -e "python[srt_hip]"; \
|
||||
else \
|
||||
python -m pip --no-cache-dir install -e "python[all_hip]"; \
|
||||
fi \
|
||||
&& cd /sgl-workspace \
|
||||
&& cp -r /sgl-workspace/sglang /sglang \
|
||||
&& python -m pip cache purge
|
||||
|
||||
# Install common Python packages
|
||||
RUN pip install IPython orjson python-multipart torchao pybind11
|
||||
|
||||
# Rebuild Triton
|
||||
RUN pip uninstall -y triton || true \
|
||||
&& git clone ${TRITON_REPO} \
|
||||
&& cd triton \
|
||||
&& git checkout ${TRITON_COMMIT} \
|
||||
&& cd python \
|
||||
&& python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
|
||||
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942 --amdgpu-lower-module-lds-strategy=1"
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
|
||||
# Build aiter
|
||||
#version: Commit 9d11f47
|
||||
# && git checkout ${AITER_COMMIT} \
|
||||
RUN pip uninstall -y aiter || true
|
||||
RUN git clone ${AITER_REPO} \
|
||||
&& cd aiter \
|
||||
&& git checkout ${AITER_COMMIT} \
|
||||
&& git submodule sync \
|
||||
&& git submodule update --init --recursive \
|
||||
&& PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
# && PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py develop \
|
||||
# && PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py develop \
|
||||
|
||||
# Copy MI300X config
|
||||
RUN find /sgl-workspace/sglang/python/sglang/srt/layers/quantization/configs/ \
|
||||
/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs/ \
|
||||
-type f -name '*MI300X*' | \
|
||||
xargs -I {} sh -c 'vf_config=$(echo "$1" | sed "s/MI300X/MI300X_VF/"); cp "$1" "$vf_config"' -- {}
|
||||
|
||||
# Environment setup complete.
|
||||
RUN echo "Environment setup complete."
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
###############vllm v0.8.5#################
|
||||
###########################################
|
||||
# ENV GITHUB_USERNAME=yushengsu-thu
|
||||
# ENV GITHUB_MAIL=yushengsu@gmail.com
|
||||
|
||||
# RUN git config --global user.name "${GITHUB_USERNAME}" \
|
||||
# && git config --global user.email "${GITHUB_MAIL}"
|
||||
|
||||
WORKDIR /workspace/
|
||||
|
||||
ENV VLLM_TARGET_DEVICE=rocm
|
||||
ENV ROCM_PATH=/opt/rocm
|
||||
ENV SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev
|
||||
|
||||
# Find the repo path in: DockerFile/Dockerfile.rocm_yang
|
||||
# RUN git clone https://github.com/RLFoundation/vllm-patch.git
|
||||
RUN pip uninstall -y vllm || true
|
||||
RUN rm -rf vllm-patch
|
||||
RUN git clone https://github.com/RLFoundation/vllm-patch.git \
|
||||
&& cd vllm-patch \
|
||||
&& git checkout v0.8.5-sleep-numa \
|
||||
&& rm -rf build/ dist/ *.egg-info \
|
||||
&& ln -sf /opt/rocm/lib/libamdhip64.so /usr/lib/libamdhip64.so \
|
||||
&& SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py install
|
||||
# RUN SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py develop
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#########################################
|
||||
#### Install megatron-core###############
|
||||
#########################################
|
||||
RUN pip uninstall -y megatron-core && \
|
||||
git clone https://github.com/yushengsu-thu/Megatron-LM-amd_version.git && \
|
||||
cd Megatron-LM-amd_version && \
|
||||
pip install -vvv -e . && \
|
||||
cd /workspace/
|
||||
#########################################
|
||||
#########################################
|
||||
#########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#######################################
|
||||
################apex###################
|
||||
#######################################
|
||||
WORKDIR /workspace/
|
||||
RUN pip uninstall -y apex && \
|
||||
git clone https://github.com/ROCm/apex.git && \
|
||||
cd apex && \
|
||||
python setup.py install && \
|
||||
cd /workspace/
|
||||
#######################################
|
||||
#######################################
|
||||
#######################################
|
||||
|
||||
|
||||
|
||||
|
||||
################################################################################
|
||||
###########################Add torch_memory_saver###############################
|
||||
################################################################################
|
||||
# Set environment variables
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--amdgpu-target=gfx90a;gfx942 -D__HIP_PLATFORM_AMD__"
|
||||
ENV CFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
ENV CXXFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
RUN pip install "git+https://github.com/YangWang92/torch_memory_saver_numa.git@numa"
|
||||
################################################################################
|
||||
################################################################################
|
||||
################################################################################
|
||||
|
||||
|
||||
|
||||
########################################
|
||||
######Install ray#######################
|
||||
########################################
|
||||
# need to add this patch: https://github.com/ray-project/ray/pull/53531/files
|
||||
RUN pip uninstall ray -y
|
||||
RUN pip install "ray[data,train,tune,serve]>=2.47.0"
|
||||
########################################
|
||||
########################################
|
||||
########################################
|
||||
|
||||
|
||||
|
||||
##########################################
|
||||
#######Install other dependencies#########
|
||||
##########################################
|
||||
RUN pip install "tensordict==0.6.2" --no-deps && \
|
||||
pip install accelerate \
|
||||
codetiming \
|
||||
datasets \
|
||||
dill \
|
||||
hydra-core \
|
||||
liger-kernel \
|
||||
numpy \
|
||||
pandas \
|
||||
peft \
|
||||
"pyarrow>=15.0.0" \
|
||||
pylatexenc \
|
||||
torchdata \
|
||||
wandb \
|
||||
orjson \
|
||||
pybind11
|
||||
|
||||
WORKDIR /workspace/
|
||||
RUN git clone https://github.com/volcengine/verl.git && \
|
||||
cd verl && \
|
||||
pip install -e .
|
||||
##########################################
|
||||
##########################################
|
||||
##########################################
|
||||
|
||||
|
||||
|
||||
WORKDIR /workspace/
|
||||
|
||||
CMD ["/usr/bin/bash"]
|
||||
CMD ["/usr/bin/bash"]
|
||||
@ -1,7 +1,7 @@
|
||||
Getting started with AMD (ROCM Kernel)
|
||||
=====================================================
|
||||
|
||||
Last updated: 06/02/2025.
|
||||
Last updated: 07/06/2025.
|
||||
|
||||
Author: `Yusheng Su <https://yushengsu-thu.github.io/>`_
|
||||
|
||||
@ -16,40 +16,267 @@ docker/Dockerfile.rocm
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
# Build the docker in the repo dir:
|
||||
# docker build -f docker/Dockerfile.rocm -t verl-rocm .
|
||||
# docker images # you can find your built docker
|
||||
FROM "rlfoundation.azurecr.io/rocm6.3.4:vllm-0.8.5-numa-patch-ubuntu-22.04"
|
||||
|
||||
SHELL ["/bin/bash", "-ceuxo", "pipefail"]
|
||||
|
||||
ENV MAX_JOBS=512
|
||||
|
||||
ENV PATH="/usr/local/python3.12/bin:$PATH"
|
||||
RUN ln -sf /usr/bin/python3.12 /usr/bin/python && \
|
||||
ln -sf /usr/bin/pip3.12 /usr/bin/pip
|
||||
|
||||
############################################
|
||||
RUN apt-get update
|
||||
RUN apt-get install -y pkg-config liblzma-dev
|
||||
############################################
|
||||
|
||||
###########################################
|
||||
##########Install TransformerEngine########
|
||||
###########################################
|
||||
WORKDIR /workspace/
|
||||
# transformer-engine install
|
||||
# https://github.com/ROCm/TransformerEngine
|
||||
RUN rm -rf TransformerEngine
|
||||
RUN git clone --recursive https://github.com/ROCm/TransformerEngine.git
|
||||
WORKDIR /workspace/TransformerEngine
|
||||
git checkout 236178e5
|
||||
# git checkout bb061ade
|
||||
# git checkout 864405c
|
||||
ENV NVTE_FRAMEWORK=pytorch
|
||||
ENV NVTE_ROCM_ARCH=gfx942
|
||||
ENV NVTE_USE_HIPBLASLT=1
|
||||
ENV NVTE_USE_ROCM=1
|
||||
# export CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr:${CMAKE_PREFIX_PATH:-}"
|
||||
ENV CMAKE_PREFIX_PATH="/opt/rocm:/opt/rocm/hip:/usr/local:/usr"
|
||||
RUN MAX_JOBS=$(MAX_JOBS) pip install . -vvv
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
# Support - Traing: fsdp; Inference: vllm
|
||||
# FROM rocm/vllm:rocm6.2_mi300_ubuntu20.04_py3.9_vllm_0.6.4
|
||||
# Support - Traing: fsdp; Inference: vllm, sglang
|
||||
FROM lmsysorg/sglang:v0.4.6.post5-rocm630
|
||||
|
||||
# Set working directory
|
||||
# WORKDIR $PWD/app
|
||||
|
||||
# Set environment variables
|
||||
|
||||
####################################################################################
|
||||
################Install vllm - sglang require vllm 0.6.7 dependency#################
|
||||
####################################################################################
|
||||
#### Require vllm 0.6.7 - checkout 113274a0
|
||||
WORKDIR /workspace/
|
||||
RUN rm -rf vllm
|
||||
RUN pip uninstall -y vllm
|
||||
# Refer to here (down-grade vllm to 0.6.3): https://docs.vllm.ai/en/v0.6.3/getting_started/amd-installation.html
|
||||
RUN git clone https://github.com/ROCm/vllm.git
|
||||
# git clone https://github.com/vllm-project/vllm.git
|
||||
WORKDIR /workspace/vllm
|
||||
RUN git checkout 113274a0
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
#ENV MAX_JOBS=512
|
||||
ENV MAX_JOBS=${MAX_JOBS}
|
||||
RUN pip install "boto3>=1.26.0"
|
||||
RUN pip install setuptools_scm
|
||||
# will add src into py. You can delete the repo
|
||||
RUN python3 setup.py install
|
||||
WORKDIR /workspace/
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
####################################################################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############For hack docker################
|
||||
###########################################
|
||||
RUN pip install setuptools==75.8.0
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
############build sgalng###################
|
||||
###########################################
|
||||
# Set environment variables
|
||||
ENV BASE_DIR=/sgl-workspace
|
||||
ENV BUILD_TYPE=all
|
||||
ENV SGL_REPO=https://github.com/sgl-project/sglang
|
||||
ENV SGL_BRANCH=v0.4.6.post5
|
||||
ENV TRITON_REPO=https://github.com/ROCm/triton.git
|
||||
ENV TRITON_COMMIT=improve_fa_decode_3.0.0
|
||||
ENV AITER_REPO=https://github.com/ROCm/aiter.git
|
||||
ENV AITER_COMMIT=v0.1.2
|
||||
# v0.1.2 version - commit id: 9d11f47
|
||||
# ENV AITER_COMMIT=9d11f47
|
||||
ENV HIP_FORCE_DEV_KERNARG=1
|
||||
ENV HSA_NO_SCRATCH_RECLAIM=1
|
||||
ENV SGLANG_SET_CPU_AFFINITY=1
|
||||
ENV SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1
|
||||
ENV NCCL_MIN_NCHANNELS=112
|
||||
ENV MOE_PADDING=1
|
||||
ENV VLLM_FP8_PADDING=1
|
||||
ENV VLLM_FP8_ACT_PADDING=1
|
||||
ENV VLLM_FP8_WEIGHT_PADDING=1
|
||||
ENV VLLM_FP8_REDUCE_CONV=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE=1
|
||||
ENV TORCHINDUCTOR_MAX_AUTOTUNE_POINTWISE=1
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
ENV AMDGPU_TARGETS=gfx942
|
||||
ENV ROCM_ARCH=gfx942
|
||||
ENV PYTORCH_ROCM_ARCH="gfx90a;gfx942"
|
||||
# Switch to working directory
|
||||
WORKDIR /sgl-workspace
|
||||
# Clean and create directory
|
||||
RUN rm -rf /sgl-workspace && mkdir -p /sgl-workspace
|
||||
|
||||
# Clone and build sglang
|
||||
RUN git clone ${SGL_REPO} \
|
||||
&& cd sglang \
|
||||
&& git checkout ${SGL_BRANCH} || echo "Using default branch" \
|
||||
&& cd sgl-kernel \
|
||||
&& rm -f pyproject.toml \
|
||||
&& mv pyproject_rocm.toml pyproject.toml \
|
||||
&& python setup_rocm.py install \
|
||||
&& cd .. \
|
||||
&& if [ "$BUILD_TYPE" = "srt" ]; then \
|
||||
python -m pip --no-cache-dir install -e "python[srt_hip]"; \
|
||||
else \
|
||||
python -m pip --no-cache-dir install -e "python[all_hip]"; \
|
||||
fi \
|
||||
&& cd /sgl-workspace \
|
||||
&& cp -r /sgl-workspace/sglang /sglang \
|
||||
&& python -m pip cache purge
|
||||
|
||||
# Install common Python packages
|
||||
RUN pip install IPython orjson python-multipart torchao pybind11
|
||||
# Rebuild Triton
|
||||
RUN pip uninstall -y triton || true \
|
||||
&& git clone ${TRITON_REPO} \
|
||||
&& cd triton \
|
||||
&& git checkout ${TRITON_COMMIT} \
|
||||
&& cd python \
|
||||
&& python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942 --amdgpu-lower-module-lds-strategy=1"
|
||||
# ENV HIPCC_COMPILE_FLAGS_APPEND="--offload-arch=gfx942"
|
||||
|
||||
# Build aiter
|
||||
#version: Commit 9d11f47
|
||||
# && git checkout ${AITER_COMMIT} \
|
||||
RUN pip uninstall -y aiter || true
|
||||
RUN git clone ${AITER_REPO} \
|
||||
&& cd aiter \
|
||||
&& git checkout ${AITER_COMMIT} \
|
||||
&& git submodule sync \
|
||||
&& git submodule update --init --recursive \
|
||||
&& PREBUILD_KERNELS=1 GPU_ARCHS=gfx942 python3 setup.py install \
|
||||
&& cd /sgl-workspace
|
||||
|
||||
# Copy MI300X config
|
||||
RUN find /sgl-workspace/sglang/python/sglang/srt/layers/quantization/configs/ \
|
||||
/sgl-workspace/sglang/python/sglang/srt/layers/moe/fused_moe_triton/configs/ \
|
||||
-type f -name '*MI300X*' | \
|
||||
xargs -I {} sh -c 'vf_config=$(echo "$1" | sed "s/MI300X/MI300X_VF/"); cp "$1" "$vf_config"' -- {}
|
||||
|
||||
# Environment setup complete.
|
||||
RUN echo "Environment setup complete."
|
||||
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
###########################################
|
||||
###############vllm v0.8.5#################
|
||||
###########################################
|
||||
WORKDIR /workspace/
|
||||
|
||||
ENV VLLM_TARGET_DEVICE=rocm
|
||||
ENV ROCM_PATH=/opt/rocm
|
||||
ENV SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev
|
||||
# Find the repo path in: DockerFile/Dockerfile.rocm_yang
|
||||
# RUN git clone https://github.com/RLFoundation/vllm-patch.git
|
||||
RUN pip uninstall -y vllm || true
|
||||
RUN rm -rf vllm-patch
|
||||
RUN git clone https://github.com/RLFoundation/vllm-patch.git \
|
||||
&& cd vllm-patch \
|
||||
&& git checkout v0.8.5-sleep-numa \
|
||||
&& rm -rf build/ dist/ *.egg-info \
|
||||
&& ln -sf /opt/rocm/lib/libamdhip64.so /usr/lib/libamdhip64.so \
|
||||
&& SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py install
|
||||
# RUN SETUPTOOLS_SCM_PRETEND_VERSION=0.8.5.dev PYTORCH_ROCM_ARCH="gfx90a;gfx942" MAX_JOBS=${MAX_JOBS} python3 setup.py develop
|
||||
WORKDIR /workspace/
|
||||
###########################################
|
||||
###########################################
|
||||
###########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#########################################
|
||||
#### Install megatron-core###############
|
||||
#########################################
|
||||
RUN pip uninstall -y megatron-core && \
|
||||
git clone https://github.com/yushengsu-thu/Megatron-LM-amd_version.git && \
|
||||
cd Megatron-LM-amd_version && \
|
||||
pip install -vvv -e . && \
|
||||
cd /workspace/
|
||||
#########################################
|
||||
#########################################
|
||||
#########################################
|
||||
|
||||
|
||||
|
||||
|
||||
#######################################
|
||||
################apex###################
|
||||
#######################################
|
||||
WORKDIR /workspace/
|
||||
RUN pip uninstall -y apex && \
|
||||
git clone git@github.com:ROCm/apex.git && \
|
||||
cd apex && \
|
||||
python setup.py install && \
|
||||
cd /workspace/
|
||||
#######################################
|
||||
#######################################
|
||||
#######################################
|
||||
|
||||
|
||||
################################################################################
|
||||
###########################Add torch_memory_saver###############################
|
||||
################################################################################
|
||||
# Set environment variables
|
||||
ENV HIPCC_COMPILE_FLAGS_APPEND="--amdgpu-target=gfx90a;gfx942 -D__HIP_PLATFORM_AMD__"
|
||||
ENV CFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
ENV CXXFLAGS="-D__HIP_PLATFORM_AMD__"
|
||||
RUN pip install "git+https://github.com/YangWang92/torch_memory_saver_numa.git@numa"
|
||||
################################################################################
|
||||
################################################################################
|
||||
################################################################################
|
||||
|
||||
# Install vllm
|
||||
RUN pip uninstall -y vllm && \
|
||||
rm -rf vllm && \
|
||||
git clone -b v0.6.3 https://github.com/vllm-project/vllm.git && \
|
||||
cd vllm && \
|
||||
MAX_JOBS=$(nproc) python3 setup.py install && \
|
||||
cd .. && \
|
||||
rm -rf vllm
|
||||
|
||||
# Copy the entire project directory
|
||||
COPY . .
|
||||
|
||||
# Install dependencies
|
||||
RUN pip install "tensordict<0.6" --no-deps && \
|
||||
########################################
|
||||
######Install ray#######################
|
||||
########################################
|
||||
# need to add this patch: https://github.com/ray-project/ray/pull/53531/files
|
||||
RUN pip uninstall ray -y
|
||||
RUN pip install "ray[data,train,tune,serve]>=2.47.0"
|
||||
########################################
|
||||
########################################
|
||||
########################################
|
||||
|
||||
|
||||
##########################################
|
||||
#######Install other dependencies#########
|
||||
##########################################
|
||||
RUN pip install "tensordict==0.6.2" --no-deps && \
|
||||
pip install accelerate \
|
||||
codetiming \
|
||||
datasets \
|
||||
@ -61,16 +288,21 @@ docker/Dockerfile.rocm
|
||||
peft \
|
||||
"pyarrow>=15.0.0" \
|
||||
pylatexenc \
|
||||
"ray[data,train,tune,serve]>=2.45.0" \
|
||||
torchdata \
|
||||
transformers \
|
||||
wandb \
|
||||
orjson \
|
||||
pybind11 && \
|
||||
pip install -e . --no-deps
|
||||
pybind11
|
||||
|
||||
WORKDIR /workspace/
|
||||
RUN git clone https://github.com/volcengine/verl.git && \
|
||||
cd verl && \
|
||||
pip install -e .
|
||||
##########################################
|
||||
##########################################
|
||||
##########################################
|
||||
|
||||
# Install torch_memory_saver
|
||||
RUN pip install git+https://github.com/ExtremeViscent/torch_memory_saver.git --no-deps
|
||||
WORKDIR /workspace/
|
||||
CMD ["/usr/bin/bash"]
|
||||
|
||||
|
||||
Build the image:
|
||||
@ -78,7 +310,20 @@ Build the image:
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker build -t verl-rocm .
|
||||
docker docker/build -t verl-rocm .
|
||||
|
||||
Run the container
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Note: You can pull the docker from this DockerHub: [RLSys Foundation](https://hub.docker.com/u/yushengsuthu)
|
||||
Pull the image:
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
.. code-block:: bash
|
||||
|
||||
docker pull yushengsuthu/verl:verl-0.4.1_ubuntu-22.04_rocm6.3.4-numa-patch_vllm0.8.5_sglang0.4.6.post4
|
||||
|
||||
docker tag yushengsuthu/verl:verl-0.4.1_ubuntu-22.04_rocm6.3.4-numa-patch_vllm0.8.5_sglang0.4.6.post4 verl-rocm:latest
|
||||
|
||||
Run the container
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
@ -111,7 +356,7 @@ Example
|
||||
-------
|
||||
|
||||
Due to to special setting in AMD (ROCM) torch,
|
||||
1. If your ``ray>=2.45.0`` (default), you need to set ``RAY_EXPERIMENTAL_NOSET_HIP_VISIBLE_DEVICES`` when starting ray in verl's RLHF training.
|
||||
1. If your ``ray>=2.45.0`` (default), you need to set ``RAY_EXPERIMENTAL_NOSET_HIP_VISIBLE_DEVICES`` when starting ray in verl's RLHF training and add this [patch](https://github.com/ray-project/ray/pull/53531/files).
|
||||
2. If your ``ray<2.45.0``, you need to set ``RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES`` when starting ray in verl's RLHF training.
|
||||
Inference ``$ENGINE`` can be ``vllm`` or ``sglang``. We choose ``vllm`` as default in the following examples.
|
||||
|
||||
@ -126,6 +371,8 @@ PPO
|
||||
YOUR_RUN_NAME=r1-training_ppo-upstream
|
||||
# export HYDRA_FULL_ERROR=1
|
||||
|
||||
export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
||||
|
||||
# [ray] < 2.45.0
|
||||
#export RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
|
||||
|
||||
@ -178,6 +425,8 @@ GRPO
|
||||
# export HYDRA_FULL_ERROR=1
|
||||
# export FSDP_VERBOSE=1
|
||||
|
||||
#export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
||||
|
||||
# [ray] < 2.45.0
|
||||
#export RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
|
||||
|
||||
@ -304,6 +553,9 @@ slurm_script.sh
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
##########################################################################
|
||||
|
||||
## Assign using GPUs
|
||||
export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
||||
|
||||
### For rocm and training script
|
||||
# [ray] < 2.45.0
|
||||
#export RAY_EXPERIMENTAL_NOSET_ROCR_VISIBLE_DEVICES=1
|
||||
|
||||
@ -19,7 +19,7 @@ name = "verl"
|
||||
dynamic = ["version", "dependencies", "optional-dependencies", "authors", "urls"]
|
||||
|
||||
description = "verl: Volcano Engine Reinforcement Learning for LLM"
|
||||
license = {file = "LICENSE"} # or "Apache-2.0", if you prefer an SPDX identifier
|
||||
license = {text = "Apache-2.0"} # Changed from file to text format
|
||||
readme = {file = "README.md", content-type = "text/markdown"}
|
||||
requires-python = ">=3.8"
|
||||
|
||||
|
||||
@ -218,6 +218,7 @@ class Worker(WorkerHelper):
|
||||
else:
|
||||
cuda_val = val
|
||||
os.environ["CUDA_VISIBLE_DEVICES"] = val
|
||||
# os.environ["HIP_VISIBLE_DEVICES"] = val
|
||||
|
||||
if rocr_val:
|
||||
# You must take care if both HIP/CUDA and ROCR env vars are set as they have
|
||||
|
||||
Reference in New Issue
Block a user