mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
fix(lowest_tpm_rpm_v2.py): use a combined tpm+rpm query in async get cache, to reduce redis client calls in high traffic
This commit is contained in:
parent
c5d880b6fd
commit
9379e3d047
4 changed files with 54 additions and 28 deletions
|
@ -19,7 +19,7 @@ class PrometheusLogger:
|
|||
**kwargs,
|
||||
):
|
||||
try:
|
||||
verbose_logger.debug(f"in init prometheus metrics")
|
||||
print(f"in init prometheus metrics")
|
||||
from prometheus_client import Counter
|
||||
|
||||
self.litellm_llm_api_failed_requests_metric = Counter(
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue