phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(perf) Litellm redis router fix - ~100ms improvement (#6483)

Browse source 
* docs(exception_mapping.md): add missing exception types

Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183

* fix(main.py): register custom model pricing with specific key

Ensure custom model pricing is registered to the specific model+provider key combination

* test: make testing more robust for custom pricing

* fix(redis_cache.py): instrument otel logging for sync redis calls

ensures complete coverage for all redis cache calls

* refactor: pass parent_otel_span for redis caching calls in router

allows for more observability into what calls are causing latency issues

* test: update tests with new params

* refactor: ensure e2e otel tracing for router

* refactor(router.py): add more otel tracing acrosss router

catch all latency issues for router requests

* fix: fix linting error

* fix(router.py): fix linting error

* fix: fix test

* test: fix tests

* fix(dual_cache.py): pass ttl to redis cache

* fix: fix param

* perf(cooldown_cache.py): improve cooldown cache, to store cache results in memory for 5s, prevents redis call from being made on each request

reduces 100ms latency per call with caching enabled on router

* fix: fix test

* fix(cooldown_cache.py): handle if a result is None

* fix(cooldown_cache.py): add debug statements

* refactor(dual_cache.py): move to using an in-memory check for batch get cache, to prevent redis from being hit for every call

* fix(cooldown_cache.py): fix linting erropr
This commit is contained in:
Krish Dholakia 2024-10-29 13:58:29 -07:00 • committed by GitHub
parent 2819505893
commit 9431c1a1b5
9 changed files with 144 additions and 45 deletions
Download patch file Download diff file Expand all files Collapse all files

3
litellm/router.py
View file

@ -5153,6 +5153,7 @@ class Router:
verbose_router_logger.debug(
f"async cooldown deployments: {cooldown_deployments}"
)
verbose_router_logger.debug(f"cooldown_deployments: {cooldown_deployments}")
healthy_deployments = self._filter_cooldown_deployments(
healthy_deployments=healthy_deployments,
cooldown_deployments=cooldown_deployments,
@ -5261,7 +5262,7 @@ class Router:
_cooldown_time = self.cooldown_cache.get_min_cooldown(
model_ids=model_ids, parent_otel_span=parent_otel_span
)
_cooldown_list = _get_cooldown_deployments(
_cooldown_list = await _async_get_cooldown_deployments(
litellm_router_instance=self, parent_otel_span=parent_otel_span
)
raise RouterRateLimitError(