forked from phoenix/litellm-mirror
test(test_router_max_parallel_requests.py): more extensive testing for setting max parallel requests
This commit is contained in:
parent
7aa737cf10
commit
0f69f0b44e
3 changed files with 69 additions and 4 deletions
|
@ -2562,7 +2562,7 @@ class Router:
|
|||
"""
|
||||
model_id = deployment["model_info"]["id"]
|
||||
if client_type == "max_parallel_requests":
|
||||
cache_key = "{}_max_parallel_requests".format(model_id)
|
||||
cache_key = "{}_max_parallel_requests_client".format(model_id)
|
||||
client = self.cache.get_cache(key=cache_key, local_only=True)
|
||||
return client
|
||||
elif client_type == "async":
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue