Skip to content

[None][perf] disagg: skip per-chunk JSON parse on streaming usage rewrite #15042

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
peihu-nv merged 1 commit into from
Jun 8, 2026
Merged

[None][perf] disagg: skip per-chunk JSON parse on streaming usage rewrite #15042

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
5 changes: 5 additions & 0 deletions tensorrt_llm/serve/openai_disagg_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,6 +233,11 @@ def _rewrite_usage_sse_event_from_ctx(
event: bytes,
ctx_response: Optional[UCompletionResponse],
) -> bytes:
# Only the final chunk has a top-level `usage` to rewrite, but this ran
# json.loads on every relayed chunk. A usage field can't exist unless the
# bytes contain `"usage"`, so skip the parse when they don't.
if b'"usage"' not in event:
return event
separator_match = self._sse_separator_index(event)
separator = separator_match[1] if separator_match else b""
event_body = event[: -len(separator)] if separator else event
Expand Down
Loading