phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

use correct enum for InternalUsageCache

Browse source
This commit is contained in:
Ishaan Jaff 2024-09-26 18:33:26 -07:00
parent 16c0307eab
commit 86ebdc611f
2 changed files with 15 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/model_prices_and_context_window_backup.json
View file

@ -2454,6 +2454,17 @@
"mode": "chat", "mode": "chat",
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models" "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models"
}, },
"vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": {
"max_tokens": 8192,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "vertex_ai-llama_models",
"mode": "chat",
"supports_system_messages": true,
"source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas"
},
"vertex_ai/mistral-large@latest": { "vertex_ai/mistral-large@latest": {
"max_tokens": 8191, "max_tokens": 8191,
"max_input_tokens": 128000, "max_input_tokens": 128000,

5
litellm/proxy/utils.py
View file

@ -70,6 +70,7 @@ from litellm.proxy.hooks.max_budget_limiter import _PROXY_MaxBudgetLimiter
from litellm.proxy.hooks.parallel_request_limiter import ( from litellm.proxy.hooks.parallel_request_limiter import (
_PROXY_MaxParallelRequestsHandler, _PROXY_MaxParallelRequestsHandler,
) )
from litellm.proxy.proxy_server import UserAPIKeyCacheTTLEnum
from litellm.types.utils import CallTypes, LoggedLiteLLMParams from litellm.types.utils import CallTypes, LoggedLiteLLMParams
if TYPE_CHECKING: if TYPE_CHECKING:
@ -301,7 +302,9 @@ class ProxyLogging:
self.call_details: dict = {} self.call_details: dict = {}
self.call_details["user_api_key_cache"] = user_api_key_cache self.call_details["user_api_key_cache"] = user_api_key_cache
self.internal_usage_cache: InternalUsageCache = InternalUsageCache( self.internal_usage_cache: InternalUsageCache = InternalUsageCache(
dual_cache=DualCache(default_in_memory_ttl=1) # ping redis cache every 1s dual_cache=DualCache(
default_in_memory_ttl=UserAPIKeyCacheTTLEnum.in_memory_cache_ttl.value
) # ping redis cache every 1s
) )
self.max_parallel_request_limiter = _PROXY_MaxParallelRequestsHandler( self.max_parallel_request_limiter = _PROXY_MaxParallelRequestsHandler(
self.internal_usage_cache self.internal_usage_cache