Skip to content

Logging cache_hit_rate only for prefill and speculative_decoding metrics only for decode #12460

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −5
Open

Logging cache_hit_rate only for prefill and speculative_decoding metrics only for decode #12460

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion python/sglang/srt/managers/scheduler_metrics_mixin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -331,7 +331,7 @@ def log_decode_stats(

# Others
self.calculate_utilization()
self.metrics_collector.log_stats(self.stats)
self.metrics_collector.log_stats(self.stats, is_decode_stats=True)
self._emit_kv_metrics()
self._publish_kv_events()

Expand Down
11 changes: 7 additions & 4 deletions python/sglang/srt/metrics/collector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -529,7 +529,7 @@ def observe_per_stage_req_latency(self, stage: str, latency: float) -> None:
def observe_queue_time(self, latency: float) -> None:
self._log_histogram(self.queue_time, latency)

def log_stats(self, stats: SchedulerStats) -> None:
def log_stats(self, stats: SchedulerStats, is_decode_stats: bool = False) -> None:
self._log_gauge(self.num_running_reqs, stats.num_running_reqs)
self._log_gauge(self.num_used_tokens, stats.num_used_tokens)
self._log_gauge(self.token_usage, stats.token_usage)
Expand All @@ -543,11 +543,14 @@ def log_stats(self, stats: SchedulerStats) -> None:
self._log_gauge(
self.num_running_reqs_offline_batch, stats.num_running_reqs_offline_batch
)
self._log_gauge(self.cache_hit_rate, stats.cache_hit_rate)

if not is_decode_stats:
self._log_gauge(self.cache_hit_rate, stats.cache_hit_rate)

# Speculative decoding
self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)
if is_decode_stats:
self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)
Comment on lines +547 to +553
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Oct 31, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

Since logging cache_hit_rate and speculative decoding metrics are mutually exclusive based on is_decode_stats, you can use a single if/else block. This improves readability and makes the mutually exclusive nature of these logic blocks more explicit.

Suggested change
if not is_decode_stats:
self._log_gauge(self.cache_hit_rate, stats.cache_hit_rate)
# Speculative decoding
self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)
if is_decode_stats:
self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)
if not is_decode_stats:
self._log_gauge(self.cache_hit_rate, stats.cache_hit_rate)
else:
# Speculative decoding
self._log_gauge(self.spec_accept_length, stats.spec_accept_length)
self._log_gauge(self.spec_accept_rate, stats.spec_accept_rate)


# PD disaggregation
self._log_gauge(
Expand Down