huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 11:54:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

DockerFile change

Browse Source
This commit is contained in:
Ankit Singh 2023-07-01 13:37:43 +00:00 committed by ankit201
parent e943a294bc
commit 15de7c7ac3
1 changed files with 9 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
Dockerfile
View File

@ -88,6 +88,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
RUN /opt/conda/bin/conda install -c "nvidia/label/cuda-11.8.0" cuda==11.8 && \
/opt/conda/bin/conda clean -ya
# Build Flash Attention CUDA kernels
FROM kernel-builder as flash-att-builder
@ -108,18 +109,8 @@ COPY server/custom_kernels/ .
# Build specific version of transformers
RUN python setup.py build
# Build vllm CUDA kernels
FROM kernel-builder as vllm-builder
WORKDIR /usr/src
COPY server/Makefile-vllm Makefile
# Build specific version of vllm
RUN make build-vllm
# Text Generation Inference base image
FROM nvidia/cuda:11.8.0-base-ubuntu20.04 as base
FROM nvidia/cuda:11.8.0-base-ubuntu22.04 as base
# Conda env
ENV PATH=/opt/conda/bin:$PATH \
@ -134,10 +125,16 @@ WORKDIR /usr/src
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
libssl-dev \
openssl\
wget\
ca-certificates \
make \
&& rm -rf /var/lib/apt/lists/*
RUN wget http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.0g-2ubuntu4_amd64.deb
RUN dpkg -i libssl1.1_1.1.0g-2ubuntu4_amd64.deb
# Copy conda with PyTorch installed
COPY --from=pytorch-install /opt/conda /opt/conda
@ -146,12 +143,9 @@ COPY --from=flash-att-builder /usr/src/flash-attention/build/lib.linux-x86_64-cp
COPY --from=flash-att-builder /usr/src/flash-attention/csrc/layer_norm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
COPY --from=flash-att-builder /usr/src/flash-attention/csrc/rotary/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Copy build artifacts from custom kernels builder
# Copy build artifacts from transformers builder
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39/custom_kernels /usr/src/custom-kernels/src/custom_kernels
# Copy builds artifacts from vllm builder
COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Install flash-attention dependencies
RUN pip install einops --no-cache-dir