20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[V1] Remove log noise when idle (#16735)

Browse Source 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
This commit is contained in:
Russell Bryant 2025-04-17 00:34:08 -04:00 committed by GitHub
parent 607029e515
commit 9dbf7a2dc1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 15 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
vllm/v1/metrics/loggers.py
View File

@ -40,6 +40,8 @@ class LoggingStatLogger(StatLoggerBase):
# TODO: Make the interval configurable.
self.prefix_caching_metrics = PrefixCachingMetrics()
self.spec_decoding_metrics = SpecDecodingMetrics()
self.last_prompt_throughput: float = 0.0
self.last_generation_throughput: float = 0.0
def _reset(self, now):
self.last_log_time = now
@ -83,8 +85,17 @@ class LoggingStatLogger(StatLoggerBase):
scheduler_stats = self.last_scheduler_stats
log_fn = logger.info
if not any(
(prompt_throughput, generation_throughput,
self.last_prompt_throughput, self.last_generation_throughput)):
# Avoid log noise on an idle production system
log_fn = logger.debug
self.last_generation_throughput = generation_throughput
self.last_prompt_throughput = prompt_throughput
# Format and print output.
logger.info(
log_fn(
"Engine %03d: "
"Avg prompt throughput: %.1f tokens/s, "
"Avg generation throughput: %.1f tokens/s, "
@ -101,7 +112,7 @@ class LoggingStatLogger(StatLoggerBase):
)
if scheduler_stats.spec_decoding_stats is not None:
self.spec_decoding_metrics.log()
self.spec_decoding_metrics.log(log_fn=log_fn)
class PrometheusStatLogger(StatLoggerBase):

4
vllm/v1/spec_decode/metrics.py
View File

@ -43,14 +43,14 @@ class SpecDecodingMetrics:
self.num_accepted_tokens.append(
spec_decoding_stats.num_accepted_tokens)
def log(self):
def log(self, log_fn=logger.info):
num_draft_tokens = np.sum(self.num_draft_tokens)
num_accepted_tokens = np.sum(self.num_accepted_tokens)
draft_acceptance_rate = (num_accepted_tokens / num_draft_tokens *
100 if num_draft_tokens > 0 else float("nan"))
logger.info(
log_fn(
"SpecDecoding metrics: "
"Draft acceptance rate: %.1f%%, "
"Accepted: %d tokens, "