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
Build docker image with shared objects from "build" step (#2237)
Alexandre Payot committed
Jan 4, 2024 at 18:35 UTC
937e7b7d7c460c00805ac358a4873ec0653ab2f5
2 files changed
+1
-1
.dockerignore
new
+1
@@ -0,0 +1 @@
1
+vllm/*.so
Dockerfile
-1
@@ -81,4 +81,3 @@ COPY --from=build /workspace/vllm/*.so /workspace/vllm/
81
COPY vllm vllm
82
83
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
84
-