ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(proxy/utils.py): uncomment max parallel request limit check

Browse Source
This commit is contained in:
Krrish Dholakia 2024-03-30 20:51:59 -07:00
parent 364526d0bc
commit 3b8e7241b4
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
litellm/proxy/utils.py
View File

@ -55,7 +55,7 @@ class ProxyLogging:
## INITIALIZE LITELLM CALLBACKS ##
self.call_details: dict = {}
self.call_details["user_api_key_cache"] = user_api_key_cache
# self.max_parallel_request_limiter = _PROXY_MaxParallelRequestsHandler()
self.max_parallel_request_limiter = _PROXY_MaxParallelRequestsHandler()
self.max_tpm_rpm_limiter = _PROXY_MaxTPMRPMLimiter(
redis_usage_cache=redis_usage_cache
)
@ -74,7 +74,7 @@ class ProxyLogging:
def _init_litellm_callbacks(self):
print_verbose(f"INITIALIZING LITELLM CALLBACKS!")
# litellm.callbacks.append(self.max_parallel_request_limiter)
litellm.callbacks.append(self.max_parallel_request_limiter)
litellm.callbacks.append(self.max_tpm_rpm_limiter)
litellm.callbacks.append(self.max_budget_limiter)
litellm.callbacks.append(self.cache_control_check)