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 10, 10:15 UTC
fix: remove duplicate engine_id check in nixl_connector (#31948)
Signed-off-by: Bofeng BF1 Xue <xuebf1@Lenovo.com> Co-authored-by: Bofeng BF1 Xue <xuebf1@Lenovo.com>
Bofeng Xue committed
Jan 9, 2026 at 20:13 UTC
55212c140461736b0797ff7a9470f9f9150e5b9a
1 file changed
-7
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
-7
@@ -1077,13 +1077,6 @@ class NixlConnectorWorker:
1077
) from e
1078
1079
# Ensure engine id matches.
1080
- if metadata.engine_id != expected_engine_id:
1081
- raise RuntimeError(
1082
- f"Remote NIXL agent engine ID mismatch. "
1083
- f"Expected {expected_engine_id},"
1084
- f"received {metadata.engine_id}."
1085
- )
1086
- # Ensure engine id matches.
1080
if metadata.engine_id != expected_engine_id:
1081
raise RuntimeError(
1082
f"Remote NIXL agent engine ID mismatch. "