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 15, 23:30 UTC
[Misc] Fix typo at comments at metrics.py (#13024)
Jewon Lee committed
Feb 12, 2025 at 01:20 UTC
bf3e05215c7f20baf9fcd82d8877d8453dcebf6e
1 file changed
+1
-1
vllm/engine/metrics.py
+1
-1
@@ -237,7 +237,7 @@ class Metrics:
237
documentation="Count of successfully processed requests.",
238
labelnames=labelnames + [Metrics.labelname_finish_reason])
239
240
- # Speculatie decoding stats
240
+ # Speculative decoding stats
241
self.gauge_spec_decode_draft_acceptance_rate = self._gauge_cls(
242
name="vllm:spec_decode_draft_acceptance_rate",
243
documentation="Speulative token acceptance rate.",