huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

conda install

Browse Source
This commit is contained in:
OlivierDehaene 2023-11-23 12:30:26 +01:00
parent 289eee535e
commit e5bf35435c
4 changed files with 9 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Dockerfile
View File

@ -39,10 +39,13 @@ RUN cargo build --release
# Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile
FROM nvidia/cuda:12.1.0-devel-ubuntu20.04 as pytorch-install
ARG PYTORCH_VERSION=2.1.0
ARG PYTORCH_VERSION=2.1.1
ARG PYTHON_VERSION=3.10
# Keep in sync with `server/pyproject.toml
ARG CUDA_VERSION=12.1
ARG MAMBA_VERSION=23.3.1-1
ARG CUDA_CHANNEL=nvidia
ARG INSTALL_CHANNEL=pytorch
# Automatically set by buildx
ARG TARGETPLATFORM
@ -72,12 +75,10 @@ RUN chmod +x ~/mambaforge.sh && \
RUN case ${TARGETPLATFORM} in \
"linux/arm64") exit 1 ;; \
*) /opt/conda/bin/conda update -y conda && \
/opt/conda/bin/conda install -y "python=${PYTHON_VERSION}" ;; \
/opt/conda/bin/conda install -c "${INSTALL_CHANNEL}" -c "${CUDA_CHANNEL}" -y "python=${PYTHON_VERSION}" "pytorch=$PYTORCH_VERSION" "pytorch-cuda=$(echo $CUDA_VERSION | cut -d'.' -f 1-2)" ;; \
esac && \
/opt/conda/bin/conda clean -ya
RUN pip install torch==${PYTORCH_VERSION} --extra-index-url https://download.pytorch.org/whl/cu121 --no-cache-dir
# CUDA kernels builder image
FROM pytorch-install as kernel-builder

8
server/Makefile
View File

@ -16,14 +16,10 @@ gen-server:
find text_generation_server/pb/ -type f -name "*.py" -print0 -exec sed -i -e 's/^\(import.*pb2\)/from . \1/g' {} \;
touch text_generation_server/pb/__init__.py
install-torch:
# Install specific version of torch
pip install torch==2.1.0 --extra-index-url https://download.pytorch.org/whl/cu121 --no-cache-dir
install: gen-server install-torch
install: gen-server
pip install pip --upgrade
pip install -r requirements.txt
pip install -e ".[bnb, accelerate, torch, peft]"
pip install -e ".[bnb, accelerate, quantize, peft]"
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

2
server/poetry.lock generated
View File

@ -2782,4 +2782,4 @@ torch = ["torch"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.9,<3.13"
content-hash = "354dffb296d5b93ff2df541498cf03176ca0c18639d79fdd7339cd33caecde50"
content-hash = "cd3fb4b4e4aaf100f6015afa8c9adc28c22e6c0b48752452892dc3d004c1562a"

2
server/pyproject.toml
View File

@ -31,7 +31,7 @@ einops = "^0.6.1"
texttable = { version = "^1.6.7", optional = true }
datasets = { version = "^2.14.0", optional = true }
peft = { version = "^0.4.0", optional = true }
torch = { version = "^2.1.0", optional = true }
torch = { version = "^2.1.1", optional = true }
scipy = "^1.11.1"
pillow = "^10.0.0"