huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Micro optimization.

Browse Source
This commit is contained in:
Nicolas Patry 2024-06-06 13:51:40 +02:00
parent 1ac7a112fe
commit 1c4c4d6aed
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
Dockerfile
View File

@ -225,6 +225,14 @@ RUN cd server && \
pip install -r requirements_cuda.txt && \
pip install ".[bnb, accelerate, quantize, peft, outlines]" --no-cache-dir
# Deps before the binaries
# The binaries change on every build given we burn the SHA into them
# The deps change less often.
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \
g++ \
&& rm -rf /var/lib/apt/lists/*
# Install benchmarker
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
# Install router
@ -232,10 +240,6 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/loca
# Install launcher
COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \
g++ \
&& rm -rf /var/lib/apt/lists/*
# AWS Sagemaker compatible image
FROM base as sagemaker