litellm/litellm/router_strategy
Ishaan Jaff c73ce95c01
(feat) - provider budget improvements - ensure provider budgets work with multiple proxy instances + improve latency to ~90ms (#6886)
* use 1 file for duration_in_seconds

* add to readme.md

* re use duration_in_seconds

* fix importing _extract_from_regex, get_last_day_of_month

* fix import

* update provider budget routing

* fix - remove dup test

* add support for using in multi instance environments

* test_in_memory_redis_sync_e2e

* test_in_memory_redis_sync_e2e

* fix test_in_memory_redis_sync_e2e

* fix code quality check

* fix test provider budgets

* working provider budget tests

* add fixture for provider budget routing

* fix router testing for provider budgets

* add comments on provider budget routing

* use RedisPipelineIncrementOperation

* add redis async_increment_pipeline

* use redis async_increment_pipeline

* use lower value for testing

* use redis async_increment_pipeline

* use consistent key name for increment op

* add handling for budget windows

* fix typing async_increment_pipeline

* fix set attr

* add clear doc strings

* unit testing for provider budgets

* test_redis_increment_pipeline
2024-11-24 16:36:19 -08:00
..
least_busy.py (router_strategy/) ensure all async functions use async cache methods (#6489) 2024-10-29 21:07:17 +05:30
lowest_cost.py (code quality) add ruff check PLR0915 for too-many-statements (#6309) 2024-10-18 15:36:49 +05:30
lowest_latency.py (router_strategy/) ensure all async functions use async cache methods (#6489) 2024-10-29 21:07:17 +05:30
lowest_tpm_rpm.py (router_strategy/) ensure all async functions use async cache methods (#6489) 2024-10-29 21:07:17 +05:30
lowest_tpm_rpm_v2.py fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check (#6577) 2024-11-05 22:03:44 +05:30
provider_budgets.py (feat) - provider budget improvements - ensure provider budgets work with multiple proxy instances + improve latency to ~90ms (#6886) 2024-11-24 16:36:19 -08:00
simple_shuffle.py (refactor router.py ) - PR 3 - Ensure all functions under 100 lines (#6181) 2024-10-14 21:27:54 +05:30
tag_based_routing.py [Fix] Router/ Proxy - Tag Based routing, raise correct error when no deployments found and tag filtering is on (#5745) 2024-09-17 20:24:28 -07:00