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
[BugFix] Use correct python3 binary in Docker.ppc64le entrypoint (#9492)
Signed-off-by: Varad Ahirwadkar <varad.ahirwadkar1@ibm.com>
Varad Ahirwadkar committed
Oct 21, 2024 at 23:13 UTC
ec6bd6c4c6a62f6a6d53d092ba44cc2e82cdf324
1 file changed
+1
-1
Dockerfile.ppc64le
+1
-1
@@ -33,4 +33,4 @@ WORKDIR /workspace/
33
34
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
35
36
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
36
+ENTRYPOINT ["/opt/conda/bin/python3", "-m", "vllm.entrypoints.openai.api_server"]