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

remvoe unused kernels

Browse Source
This commit is contained in:
OlivierDehaene 2024-04-12 14:18:58 +02:00 committed by Nicolas Patry
parent ee04a3d3ee
commit 772c3774df
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Dockerfile
View File

@ -248,6 +248,7 @@ ENTRYPOINT ["./entrypoint.sh"]
FROM base FROM base
COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh
RUN chmod +x /tgi-entrypoint.sh
ENTRYPOINT ["/tgi-entrypoint.sh"] ENTRYPOINT ["/tgi-entrypoint.sh"]
CMD ["--json-output"] CMD ["--json-output"]

2
server/Makefile-vllm
View File

@ -4,7 +4,7 @@ vllm-cuda:
git clone https://github.com/OlivierDehaene/vllm.git vllm git clone https://github.com/OlivierDehaene/vllm.git vllm
build-vllm-cuda: vllm-cuda build-vllm-cuda: vllm-cuda
cd vllm && git fetch && git checkout 4bec8cee87f6bb8cebaec297029713cd2082e0b2 cd vllm && git fetch && git checkout 3d4693536dcb69f036c26b016a35839b99ebed59
cd vllm && python setup.py build cd vllm && python setup.py build
install-vllm-cuda: build-vllm-cuda install-vllm-cuda: build-vllm-cuda