Skip to content

[Bugfix] Fix None value handling in trace span creation for cancelled requests #20272

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 3 commits into from
Jul 30, 2025
Merged

[Bugfix] Fix None value handling in trace span creation for cancelled requests #20272

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c660387
[Bugfix] Fix None value handling in trace span creation for cancelled…
br4mm Jun 30, 2025
2ffa3b1
Format
br4mm Jun 30, 2025
f1d5f65
Merge branch 'vllm-project:main' into bugfix/metric-none-value
br4mm Jul 30, 2025
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
27 changes: 20 additions & 7 deletions vllm/engine/llm_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1862,8 +1862,14 @@ def create_trace_span(self, seq_group: SequenceGroup) -> None:
context=trace_context,
start_time=arrival_time_nano_seconds) as seq_span:
metrics = seq_group.metrics
ttft = metrics.first_token_time - metrics.arrival_time
e2e_time = metrics.finished_time - metrics.arrival_time

# Handle potential None values for cancelled/aborted requests
ttft = (metrics.first_token_time - metrics.arrival_time
if metrics.first_token_time is not None else None)

e2e_time = (metrics.finished_time - metrics.arrival_time
if metrics.finished_time is not None else None)

seq_span.set_attribute(SpanAttributes.GEN_AI_RESPONSE_MODEL,
self.model_config.model)
seq_span.set_attribute(SpanAttributes.GEN_AI_REQUEST_ID,
Expand All @@ -1886,11 +1892,18 @@ def create_trace_span(self, seq_group: SequenceGroup) -> None:
seq.get_output_len()
for seq in seq_group.get_finished_seqs()
]))
seq_span.set_attribute(SpanAttributes.GEN_AI_LATENCY_TIME_IN_QUEUE,
metrics.time_in_queue)
seq_span.set_attribute(
SpanAttributes.GEN_AI_LATENCY_TIME_TO_FIRST_TOKEN, ttft)
seq_span.set_attribute(SpanAttributes.GEN_AI_LATENCY_E2E, e2e_time)

# Only set timing attributes if the values are available
if metrics.time_in_queue is not None:
seq_span.set_attribute(
SpanAttributes.GEN_AI_LATENCY_TIME_IN_QUEUE,
metrics.time_in_queue)
if ttft is not None:
seq_span.set_attribute(
SpanAttributes.GEN_AI_LATENCY_TIME_TO_FIRST_TOKEN, ttft)
if e2e_time is not None:
seq_span.set_attribute(SpanAttributes.GEN_AI_LATENCY_E2E,
e2e_time)
if metrics.scheduler_time is not None:
seq_span.set_attribute(
SpanAttributes.GEN_AI_LATENCY_TIME_IN_SCHEDULER,
Expand Down