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, 09:30 UTC
[Neuron] Update Dockerfile.neuron to fix build failure (#9822)
Harsha vardhan manoj Bikki committed
Oct 30, 2024 at 12:22 UTC
c787f2d81ddc25a3505a2075238f1f54233ff76b
1 file changed
+1
-1
Dockerfile.neuron
+1
-1
@@ -36,6 +36,6 @@ RUN python3 -m pip install -U \
36
37
ENV VLLM_TARGET_DEVICE neuron
38
RUN --mount=type=bind,source=.git,target=.git \
39
- pip install --no-build-isolation -v -e . \
39
+ pip install --no-build-isolation -v -e .
40
41
CMD ["/bin/bash"]