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, 18:15 UTC
[CI] Pin helion version (#37012)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Yanan Cao committed
Mar 13, 2026 at 20:25 UTC
236de72e49d94451e1b7821736a11a80f7efda5d
1 file changed
+1
-1
setup.py
+1
-1
@@ -982,7 +982,7 @@ setup(
982
# Optional deps for AMD FP4 quantization support
983
"petit-kernel": ["petit-kernel"],
984
# Optional deps for Helion kernel development
985
- "helion": ["helion"],
985
+ "helion": ["helion==0.3.2"],
986
# Optional deps for gRPC server (vllm serve --grpc)
987
"grpc": ["smg-grpc-servicer[vllm] >= 0.5.0"],
988
# Optional deps for OpenTelemetry tracing