Skip to content

[V1][Minor] Enhance SpecDecoding Metrics Log in V1 #15902

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

Merged
merged 1 commit into from
Apr 2, 2025
Merged

[V1][Minor] Enhance SpecDecoding Metrics Log in V1 #15902

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
17 changes: 10 additions & 7 deletions vllm/v1/spec_decode/metrics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,13 +47,16 @@ def log(self):
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
if num_draft_tokens > 0 else float("nan"))
draft_acceptance_rate = (num_accepted_tokens / num_draft_tokens *
100 if num_draft_tokens > 0 else float("nan"))

logger.info(
"Speculative metrics: "
"Draft acceptance rate: %.3f, "
"Number of accepted tokens: %d, "
"Number of draft tokens: %d, ", draft_acceptance_rate,
num_accepted_tokens, num_draft_tokens)
"SpecDecoding metrics: "
"Draft acceptance rate: %.1f%%, "
"Accepted: %d tokens, "
"Drafted: %d tokens",
draft_acceptance_rate,
num_accepted_tokens,
num_draft_tokens,
)
self.reset()