mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-04 13:20:12 +06:00
10627c1a0f
Some checks are pending
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Waiting to run
Build documentation / build (push) Waiting to run
Slow tests on important models (on Push - A10) / Get all modified files (push) Waiting to run
Slow tests on important models (on Push - A10) / Slow & FA2 tests (push) Blocked by required conditions
Secret Leaks / trufflehog (push) Waiting to run
Update Transformers metadata / build_and_package (push) Waiting to run
* fix * fix --------- Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
58 lines
2.9 KiB
Docker
58 lines
2.9 KiB
Docker
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-08.html
|
|
FROM nvcr.io/nvidia/pytorch:24.08-py3
|
|
LABEL maintainer="Hugging Face"
|
|
|
|
ARG DEBIAN_FRONTEND=noninteractive
|
|
|
|
ARG PYTORCH='2.7.1'
|
|
# Example: `cu102`, `cu113`, etc.
|
|
ARG CUDA='cu126'
|
|
|
|
RUN apt -y update
|
|
RUN apt install -y libaio-dev
|
|
RUN python3 -m pip install --no-cache-dir --upgrade pip
|
|
|
|
ARG REF=main
|
|
RUN git clone https://github.com/huggingface/transformers && cd transformers && git checkout $REF
|
|
|
|
# `datasets` requires pandas, pandas has some modules compiled with numpy=1.x causing errors
|
|
RUN python3 -m pip install --no-cache-dir './transformers[deepspeed-testing]' 'pandas<2' 'numpy<2'
|
|
|
|
# Install latest release PyTorch
|
|
# (PyTorch must be installed before pre-compiling any DeepSpeed c++/cuda ops.)
|
|
# (https://www.deepspeed.ai/tutorials/advanced-install/#pre-install-deepspeed-ops)
|
|
RUN python3 -m pip uninstall -y torch torchvision torchaudio && python3 -m pip install --no-cache-dir -U torch==$PYTORCH torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/$CUDA
|
|
|
|
RUN python3 -m pip install --no-cache-dir git+https://github.com/huggingface/accelerate@main#egg=accelerate
|
|
|
|
# Uninstall `transformer-engine` shipped with the base image
|
|
RUN python3 -m pip uninstall -y transformer-engine
|
|
|
|
# Uninstall `torch-tensorrt` shipped with the base image
|
|
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
|
|
# `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 .
|
|
|
|
# Pre-build **latest** DeepSpeed, so it would be ready for testing (otherwise, the 1st deepspeed test will timeout)
|
|
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 python3 -m pip install deepspeed --global-option="build_ext" --global-option="-j8" --no-cache -v --disable-pip-version-check 2>&1
|
|
|
|
# `kernels` may give different outputs (within 1e-5 range) even with the same model (weights) and the same inputs
|
|
RUN python3 -m pip uninstall -y kernels
|
|
|
|
# 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
|
|
|
|
# The base image ships with `pydantic==1.8.2` which is not working - i.e. the next command fails
|
|
RUN python3 -m pip install -U --no-cache-dir "pydantic>=2.0.0"
|
|
RUN python3 -c "from deepspeed.launcher.runner import main"
|