Dockerfile.vemlp.vllm.te

# docker buildx build --platform linux/x86_64 -t "verlai/verl:$TAG" -f docker/$FILE .

# the one in docker.io is an alias for the one veturbo
# FROM vemlp-cn-beijing.cr.volces.com/veturbo/pytorch:2.4-cu124
FROM docker.io/haibinlin/verl:v0.0.5-th2.4.0-cu124-base

# only config pip index with https://pypi.tuna.tsinghua.edu.cn/simple if needed
# unset for now
RUN pip3 config unset global.index-url

# transformers 4.47.0 contains the following bug:
# AttributeError: 'Gemma2Attention' object has no attribute '_flash_attn_uses_top_left_mask'
RUN pip3 install --no-cache-dir \
    torch==2.4.0 \
    accelerate \
    codetiming \
    dill \
    hydra-core \
    numpy \
    pybind11 \
    tensordict \
    "transformers <= 4.46.0"

RUN pip3 install --no-cache-dir flash-attn==2.7.0.post2 --no-build-isolation

# vllm depends on ray, and veRL does not support ray > 2.37
RUN pip3 install --no-cache-dir vllm==0.6.3 ray==2.10

# install apex
RUN MAX_JOBS=4 pip3 install -v --disable-pip-version-check --no-cache-dir --no-build-isolation \
    --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" \
    git+https://github.com/NVIDIA/apex

# install Transformer Engine
# - flash-attn pinned to 2.5.3 by TransformerEngine, switch to eric-haibin-lin/TransformerEngine.git@v1.7.0 to relax version req
# - install with: MAX_JOBS=1 NINJA_FLAGS="-j1" TE_BUILD_WITH_NINJA=0 to avoid OOM
# - cudnn is required by TransformerEngine
# RUN CUDNN_PATH=/opt/conda/lib/python3.11/site-packages/nvidia/cudnn \
#     pip3 install git+https://github.com/eric-haibin-lin/TransformerEngine.git@v1.7.0
RUN MAX_JOBS=1 NINJA_FLAGS="-j1" pip3 install flash-attn==2.5.3 --no-cache-dir --no-build-isolation
RUN MAX_JOBS=1 NINJA_FLAGS="-j1" pip3 install git+https://github.com/NVIDIA/TransformerEngine.git@v1.7