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