scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 115

address greptile review feedback (greploop iteration 3)

Browse source 
- fix falsy-zero bug in _compute_overhead_pct: use 'is not None' instead of truthiness check so 0.0 overhead is reported correctly
This commit is contained in:
Ishaan Jaffer 2026-02-28 18:21:21 -08:00
parent 6e9f245bbb
commit 5c9f3febd2
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/proxy/performance_endpoints/endpoints.py
View file

@ -326,6 +326,6 @@ def _compute_overhead_pct(latency_stats: dict) -> Optional[float]:
return None
avg_overhead = overhead.get("avg_ms")
avg_total = total.get("avg_ms")
if avg_overhead and avg_total and avg_total > 0:
if avg_overhead is not None and avg_total is not None and avg_total > 0:
return round((avg_overhead / avg_total) * 100, 1)
return None