xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-16 16:02:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[V1][Bugfix] Do not reset prefix caching metrics (#14235)

Browse Source
This commit is contained in:
Cody Yu 2025-03-04 20:39:13 -08:00 committed by GitHub
parent 0df25101d6
commit ade3f7d988
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/v1/metrics/loggers.py
View File

@ -34,6 +34,9 @@ class LoggingStatLogger(StatLoggerBase):
def __init__(self): def __init__(self):
self._reset(time.monotonic()) self._reset(time.monotonic())
self.last_scheduler_stats = SchedulerStats() self.last_scheduler_stats = SchedulerStats()
# Prefix cache metrics. This cannot be reset.
# TODO: Make the interval configurable.
self.prefix_caching_metrics = PrefixCachingMetrics()
def _reset(self, now): def _reset(self, now):
self.last_log_time = now self.last_log_time = now
@ -42,9 +45,6 @@ class LoggingStatLogger(StatLoggerBase):
self.num_prompt_tokens: list[int] = [] self.num_prompt_tokens: list[int] = []
self.num_generation_tokens: list[int] = [] self.num_generation_tokens: list[int] = []
# Prefix cache metrics. TODO: Make the interval configurable.
self.prefix_caching_metrics = PrefixCachingMetrics()
def _track_iteration_stats(self, iteration_stats: IterationStats): def _track_iteration_stats(self, iteration_stats: IterationStats):
# Save tracked stats for token counters. # Save tracked stats for token counters.
self.num_prompt_tokens.append(iteration_stats.num_prompt_tokens) self.num_prompt_tokens.append(iteration_stats.num_prompt_tokens)