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 17, 03:00 UTC
[Bugfix][ROCm] Add numba to Dockerfile.rocm (#3962)
Woosuk Kwon committed
Apr 10, 2024 at 07:37 UTC
bd3c144e0b8e82c9b3c5c40c6d557fe8665de5a3
1 file changed
+1
-1
Dockerfile.rocm
+1
-1
@@ -91,7 +91,7 @@ RUN if [ "$BUILD_TRITON" = "1" ]; then \
91
92
COPY ./ /app/vllm
93
94
-RUN python3 -m pip install --upgrade pip
94
+RUN python3 -m pip install --upgrade pip numba
95
RUN python3 -m pip install xformers==0.0.23 --no-deps
96
97
RUN cd /app \