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

Squashed commit of the following: (#9709)

Browse source 
commit b12a9892b7
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Wed Apr 2 08:09:56 2025 -0700

    fix(utils.py): don't modify openai_token_counter

commit 294de31803
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 21:22:40 2025 -0700

    fix: fix linting error

commit cb6e9fbe40
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:52:45 2025 -0700

    refactor: complete migration

commit bfc159172d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:09:59 2025 -0700

    refactor: refactor more constants

commit 43ffb6a558
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:45:24 2025 -0700

    fix: test

commit 04dbe4310c
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:28:58 2025 -0700

    refactor: refactor: move more constants into constants.py

commit 3c26284aff
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:14:46 2025 -0700

    refactor: migrate hardcoded constants out of __init__.py

commit c11e0de69d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:11:21 2025 -0700

    build: migrate all constants into constants.py

commit 7882bdc787
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:07:37 2025 -0700

    build: initial test banning hardcoded numbers in repo
This commit is contained in:
Krish Dholakia 2025-04-02 21:24:54 -07:00 • committed by GitHub
parent 5a722ef18f
commit 8ee32291e0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
51 changed files with 509 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

15
litellm/scheduler.py
View file

@ -6,17 +6,14 @@ from pydantic import BaseModel
from litellm import print_verbose
from litellm.caching.caching import DualCache, RedisCache
from litellm.constants import DEFAULT_IN_MEMORY_TTL, DEFAULT_POLLING_INTERVAL
class SchedulerCacheKeys(enum.Enum):
queue = "scheduler:queue"
default_in_memory_ttl = 5 # cache queue in-memory for 5s when redis cache available
class DefaultPriorities(enum.Enum):
High = 0
Medium = 128
Low = 255
default_in_memory_ttl = (
DEFAULT_IN_MEMORY_TTL # cache queue in-memory for 5s when redis cache available
)
class FlowItem(BaseModel):
@ -44,7 +41,9 @@ class Scheduler:
self.cache = DualCache(
redis_cache=redis_cache, default_in_memory_ttl=default_in_memory_ttl
)
self.polling_interval = polling_interval or 0.03 # default to 3ms
self.polling_interval = (
polling_interval or DEFAULT_POLLING_INTERVAL
) # default to 3ms
async def add_request(self, request: FlowItem):
# We use the priority directly, as lower values indicate higher priority