A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 15:45 UTC
[CI/Build] Fix missing ci dependencies (#8834)
fyuan1316 committed
Sep 27, 2024 at 02:04 UTC
68988d4e0d8765901c51f07f9bfbda58f35f6f63
1 file changed
+1
-1
.github/workflows/scripts/build.sh
+1
-1
@@ -8,7 +8,7 @@ PATH=${cuda_home}/bin:$PATH
8
LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
9
10
# Install requirements
11
-$python_executable -m pip install wheel packaging
11
+$python_executable -m pip install wheel packaging 'setuptools-scm>=8'
12
$python_executable -m pip install -r requirements-cuda.txt
13
14
# Limit the number of parallel jobs to avoid OOM