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, 05:15 UTC
[Trivial] Remove duplicate enable_mfu_metrics (#32246)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Mark McLoughlin committed
Jan 13, 2026 at 17:09 UTC
ab74b2a27a4eb88b90356bfb4b452d29edf05574
1 file changed
-3
vllm/config/observability.py
-3
@@ -72,9 +72,6 @@ class ObservabilityConfig:
72
This is for internal use only (e.g., benchmarks) and is not exposed as a CLI
73
argument."""
74
75
- enable_mfu_metrics: bool = False
76
- """Enable Model FLOPs Utilization (MFU) metrics."""
77
-
75
enable_logging_iteration_details: bool = False
76
"""Enable detailed logging of iteration details.
77
If set, vllm EngineCore will log iteration details