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 6, 19:15 UTC
build: update smg-grpc-servicer to use vllm extra (#36938)
Signed-off-by: Simo Lin <linsimo.mark@gmail.com>
Simo Lin committed
Mar 12, 2026 at 18:31 UTC
572c776bfbd530dfbc6ba8f90a021d240209f7a8
1 file changed
+1
-1
setup.py
+1
-1
@@ -983,7 +983,7 @@ setup(
983
# Optional deps for Helion kernel development
984
"helion": ["helion"],
985
# Optional deps for gRPC server (vllm serve --grpc)
986
- "grpc": ["smg-grpc-servicer >= 0.4.2"],
986
+ "grpc": ["smg-grpc-servicer[vllm] >= 0.5.0"],
987
# Optional deps for OpenTelemetry tracing
988
"otel": [
989
"opentelemetry-sdk>=1.26.0",