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

[V1][Metrics] Add request_success_total counter, labelled with finish reason (#12579)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin
2025-02-05 00:46:54 +00:00
committed by GitHub
parent 18016a5e62
commit 233df6f5c4
7 changed files with 66 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/entrypoints/openai/test_metrics.py
View File

@@ -205,6 +205,7 @@ EXPECTED_METRICS_V1 = [
"vllm:gpu_cache_usage_perc",
"vllm:prompt_tokens_total",
"vllm:generation_tokens_total",
"vllm:request_success_total",
"vllm:request_prompt_tokens_sum",
"vllm:request_prompt_tokens_bucket",
"vllm:request_prompt_tokens_count",