phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(routing.py): update token usage on streaming

Browse source
This commit is contained in:
Krrish Dholakia 2023-11-20 14:19:14 -08:00
parent 0422bba38d
commit 1976d0f7d6
4 changed files with 14 additions and 167 deletions
Download patch file Download diff file Expand all files Collapse all files

13
litellm/proxy/proxy_cli.py
View file

@ -78,12 +78,12 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
global feature_telemetry
args = locals()
if local:
from proxy_server import app, save_worker_config, usage_telemetry, add_keys_to_config
from proxy_server import app, save_worker_config, usage_telemetry
else:
try:
from .proxy_server import app, save_worker_config, usage_telemetry, add_keys_to_config
from .proxy_server import app, save_worker_config, usage_telemetry
except ImportError as e:
from proxy_server import app, save_worker_config, usage_telemetry, add_keys_to_config
from proxy_server import app, save_worker_config, usage_telemetry
feature_telemetry = usage_telemetry
if logs is not None:
if logs == 0: # default to 1
@ -105,13 +105,6 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
except:
print("LiteLLM: No logs saved!")
return
if add_key:
key_name, key_value = add_key.split("=")
add_keys_to_config(key_name, key_value)
with open(user_config_path) as f:
print(f.read())
print("\033[1;32mDone successfully\033[0m")
return
if model and "ollama" in model:
run_ollama_serve()
if test != False: