huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-12 04:44:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

misc: update vllm dependecy to support attention size 160

Browse Source
This commit is contained in:
Paolo Albano 2024-06-04 13:48:44 +00:00
parent 245d3de948
commit c50397ca3a
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
server/Makefile-vllm
View File

@ -1,9 +1,9 @@
commit_cuda := b5dfc61db88a81069e45b44f7cc99bd9e62a60fa commit_cuda := e0c577263c2c7f367198d4a51a9964136ea259db
commit_rocm := c6ee53b1be97e3bbc791b95f22827501297f8921 commit_rocm := c6ee53b1be97e3bbc791b95f22827501297f8921
build-vllm-cuda: build-vllm-cuda:
if [ ! -d 'vllm' ]; then \ if [ ! -d 'vllm' ]; then \
pip install -U ninja packaging --no-cache-dir && \ pip install -U ninja packaging --no-cache-dir && \
git clone https://github.com/Narsil/vllm.git vllm; \ git clone https://github.com/igeniusai/vllm.git vllm; \
fi fi
cd vllm && git fetch && git checkout $(commit_cuda) && python setup.py build cd vllm && git fetch && git checkout $(commit_cuda) && python setup.py build