@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 05bdf4eaf3
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, 05:30 UTC

Fix Dockerfile.rocm (#2101)

Co-authored-by: miloice <jeffaw99@hotmail.com>

TJian committed Dec 14, 2023 at 16:45 UTC 05bdf4eaf3bd8c577d09a6556acc3688094d0f6b
1 file changed +1 -1
Dockerfile.rocm
+1 -1
@@ -52,7 +52,7 @@ RUN pip install xformers==0.0.23 --no-deps
52 RUN cd /app \
53 && cd vllm \
54 && pip install -U -r requirements-rocm.txt \
55 - && bash patch_xformers-0.0.23.rocm.sh \
55 + && bash patch_xformers.rocm.sh \
56 && python3 setup.py install \
57 && cd ..
58