Fix nccl regression on PyTorch 2.3 upgrade (#2099)

* fix nccl issue

* add note in dockerfile

* use v2.22.3 that also fixes @samsamoa's repro

* poetry actually can't handle the conflict between torch and nccl

* set LD_PRELOAD
This commit is contained in:
fxmarty 2024-07-08 17:52:10 +02:00 committed by GitHub
parent 87ebb6477b
commit 4c50b6d04b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 2 deletions

View File

@ -40,7 +40,9 @@ RUN cargo build --profile release-opt
# Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS pytorch-install
# NOTE: When updating PyTorch version, beware to remove `pip install nvidia-nccl-cu12==2.22.3` below in the Dockerfile. Context: https://github.com/huggingface/text-generation-inference/pull/2099
ARG PYTORCH_VERSION=2.3.0
ARG PYTHON_VERSION=3.10
# Keep in sync with `server/pyproject.toml
ARG CUDA_VERSION=12.1
@ -241,7 +243,10 @@ COPY server/Makefile server/Makefile
RUN cd server && \
make gen-server && \
pip install -r requirements_cuda.txt && \
pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir
pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir && \
pip install nvidia-nccl-cu12==2.22.3
ENV LD_PRELOAD=/opt/conda/lib/python3.10/site-packages/nvidia/nccl/lib/libnccl.so.2
# Deps before the binaries
# The binaries change on every build given we burn the SHA into them

View File

@ -35,5 +35,5 @@ run-dev:
SAFETENSORS_FAST_GPU=1 python -m torch.distributed.run --nproc_per_node=2 text_generation_server/cli.py serve bigscience/bloom-560m --sharded
export-requirements:
poetry export -o requirements_cuda.txt --without-hashes
poetry export -o requirements_cuda.txt --without-hashes --with cuda
poetry export -o requirements_rocm.txt --without-hashes