biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1][Metrics] Add TTFT and TPOT histograms (#12530)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin
2025-01-29 04:11:16 +00:00
committed by GitHub
parent dd6a3a02cb
commit 46fb056749
4 changed files with 45 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/entrypoints/openai/test_metrics.py
View File

@@ -208,6 +208,12 @@ EXPECTED_METRICS_V1 = [
"vllm:request_generation_tokens_sum",
"vllm:request_generation_tokens_bucket",
"vllm:request_generation_tokens_count",
"vllm:time_to_first_token_seconds_sum",
"vllm:time_to_first_token_seconds_bucket",
"vllm:time_to_first_token_seconds_count",
"vllm:time_per_output_token_seconds_sum",
"vllm:time_per_output_token_seconds_bucket",
"vllm:time_per_output_token_seconds_count",
]