@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / bd3c144e0b
Fork 0

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 \