mirror of
https://github.com/volcengine/verl.git
synced 2025-10-20 21:53:50 +08:00
21b99ed741
### What does this PR do? > This PR adds tensorboard as a dependency to requirements.txt file, across several Dockerfiles (Dockerfile.ngc.vllm, Dockerfile.ngc.vllm0.8, Dockerfile.ngc.vllm0.8.sagemaker), a setup script (install_vllm_sglang_mcore.sh), and the main setup.py file. This change ensures that the tensorboard package is consistently installed, enabling visualization of training metrics for various configurations and deployment environments. This is a maintenance task that enhances the project's observability without altering core functionality. ### Test > This change is a dependency update and doesn't require specific testing beyond confirming the installation is successful. ### API and Usage Example > No API changes are introduced. The usage of TensorBoard would be initiated by the user after installing the requirements. ```python # No code snippet is applicable for this change
76 lines
3.3 KiB
Docker
76 lines
3.3 KiB
Docker
# Start from the NVIDIA official image (ubuntu-22.04 + cuda-12.6 + python-3.10)
|
|
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-08.html
|
|
FROM nvcr.io/nvidia/pytorch:24.08-py3
|
|
|
|
# Define environments
|
|
ENV MAX_JOBS=32
|
|
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ENV NODE_OPTIONS=""
|
|
ENV PIP_ROOT_USER_ACTION=ignore
|
|
ENV HF_HUB_ENABLE_HF_TRANSFER="1"
|
|
|
|
# Define installation arguments
|
|
ARG APT_SOURCE=https://mirrors.tuna.tsinghua.edu.cn/ubuntu/
|
|
ARG PIP_INDEX=https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
|
|
|
|
# Set apt source
|
|
RUN cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
|
|
{ \
|
|
echo "deb ${APT_SOURCE} jammy main restricted universe multiverse"; \
|
|
echo "deb ${APT_SOURCE} jammy-updates main restricted universe multiverse"; \
|
|
echo "deb ${APT_SOURCE} jammy-backports main restricted universe multiverse"; \
|
|
echo "deb ${APT_SOURCE} jammy-security main restricted universe multiverse"; \
|
|
} > /etc/apt/sources.list
|
|
|
|
# Install systemctl
|
|
RUN apt-get update && \
|
|
apt-get install -y -o Dpkg::Options::="--force-confdef" systemd && \
|
|
apt-get clean
|
|
|
|
# Install tini
|
|
RUN apt-get update && \
|
|
apt-get install -y tini && \
|
|
apt-get clean
|
|
|
|
# Change pip source
|
|
RUN pip config set global.index-url "${PIP_INDEX}" && \
|
|
pip config set global.extra-index-url "${PIP_INDEX}" && \
|
|
python -m pip install --upgrade pip
|
|
|
|
# Uninstall nv-pytorch fork
|
|
RUN pip uninstall -y torch torchvision torchaudio \
|
|
pytorch-quantization pytorch-triton torch-tensorrt \
|
|
xgboost transformer_engine flash_attn apex megatron-core grpcio
|
|
|
|
# Install torch-2.6.0+cu124 + vllm-0.8.3
|
|
# torch-2.6.0+cu124: cxx11abi=False
|
|
# torch-2.6.0+cu126: cxx11abi=True
|
|
# see https://github.com/flashinfer-ai/flashinfer/issues/911
|
|
RUN pip install --no-cache-dir "vllm==0.8.3" "torch==2.6.0" "torchvision==0.21.0" "torchaudio==2.6.0" "tensordict==0.6.2" torchdata \
|
|
"transformers[hf_xet]>=4.51.0" accelerate datasets peft hf-transfer \
|
|
"numpy<2.0.0" "pyarrow>=15.0.0" pandas \
|
|
ray[default] codetiming hydra-core pylatexenc qwen-vl-utils wandb dill pybind11 liger-kernel mathruler \
|
|
pytest py-spy pyext pre-commit ruff tensorboard
|
|
|
|
# Install flash-attn-2.7.4.post1 (cxx11abi=False)
|
|
RUN wget -nv https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.4.post1/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl && \
|
|
pip install --no-cache-dir flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
|
|
|
|
# Install flashinfer-0.2.2.post1+cu124 (cxx11abi=False)
|
|
# vllm-0.8.3 does not support flashinfer>=0.2.3
|
|
# see https://github.com/vllm-project/vllm/pull/15777
|
|
RUN wget -nv https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.2.post1/flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl && \
|
|
pip install --no-cache-dir flashinfer_python-0.2.2.post1+cu124torch2.6-cp38-abi3-linux_x86_64.whl
|
|
|
|
# Fix packages
|
|
RUN pip uninstall -y pynvml nvidia-ml-py && \
|
|
pip install --no-cache-dir --upgrade "nvidia-ml-py>=12.560.30" "fastapi[standard]>=0.115.0" "optree>=0.13.0" "pydantic>=2.9" "grpcio>=1.62.1"
|
|
|
|
# Install verl
|
|
RUN pip install --no-cache-dir verl[vllm] -U
|
|
|
|
# Reset pip config
|
|
RUN pip config unset global.index-url && \
|
|
pip config unset global.extra-index-url
|