ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
44e7ffd05c
litellm/tests
History
Krish Dholakia 44e7ffd05c
(perf) Litellm redis router fix - ~100ms improvement (#6483) 
* 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
2024-10-29 13:58:29 -07:00
..
code_coverage_tests (router_strategy/) ensure all async functions use async cache methods (#6489) 2024-10-29 21:07:17 +05:30
documentation_tests Litellm dev 10 26 2024 (#6472) 2024-10-28 15:05:43 -07:00
llm_translation LiteLLM Minor Fixes & Improvements (10/24/2024) (#6441) 2024-10-28 15:05:20 -07:00
load_tests (load testing) add vertex_ai embeddings load test (#6004) 2024-10-03 14:39:15 +05:30
local_testing (perf) Litellm redis router fix - ~100ms improvement (#6483) 2024-10-29 13:58:29 -07:00
logging_callback_tests (fix) Prometheus - Log Postgres DB latency, status on prometheus (#6484) 2024-10-29 12:17:35 +05:30
old_proxy_tests/tests Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
otel_tests (feat) prometheus have well defined latency buckets (#6211) 2024-10-14 17:16:01 +05:30
pass_through_tests test(skip-flaky-google-context-caching-test): google is not reliable. their sample code is also not working 2024-10-22 12:06:30 -07:00
proxy_admin_ui_tests add unit testing for non_proxy_admin_allowed_routes_check 2024-10-25 13:04:37 +04:00
router_unit_tests (perf) Litellm redis router fix - ~100ms improvement (#6483) 2024-10-29 13:58:29 -07:00
gettysburg.wav feat(main.py): support openai transcription endpoints 2024-03-08 10:25:19 -08:00
large_text.py fix(router.py): check for context window error when handling 400 status code errors 2024-03-26 08:08:15 -07:00
openai_batch_completions.jsonl feat(router.py): Support Loadbalancing batch azure api endpoints (#5469) 2024-09-02 21:32:55 -07:00
README.MD Update README.MD 2024-03-29 14:56:41 -07:00
test_callbacks_on_proxy.py fix - test num callbacks 2024-05-17 22:06:51 -07:00
test_config.py mark test_team_logging as flaky 2024-09-04 20:29:21 -07:00
test_debug_warning.py fix(utils.py): fix togetherai streaming cost calculation 2024-08-01 15:03:08 -07:00
test_end_users.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
test_entrypoint.py (fix) clean up root repo - move entrypoint.sh and build_admin_ui to /docker (#6110) 2024-10-08 11:34:43 +05:30
test_fallbacks.py fix(user_api_key_auth.py): ensure user has access to fallback models 2024-06-20 16:02:19 -07:00
test_health.py (test) /health/readiness 2024-01-29 15:27:25 -08:00
test_keys.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
test_logging.conf feat(proxy_cli.py): add new 'log_config' cli param (#6352) 2024-10-21 21:25:58 -07:00
test_models.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
test_openai_batches_endpoint.py test batches endpoint on proxy 2024-07-30 09:46:30 -07:00
test_openai_endpoints.py Litellm fix router testing (#5748) 2024-09-17 18:02:23 -07:00
test_openai_files_endpoints.py test - batches endpoint 2024-07-26 18:09:49 -07:00
test_openai_fine_tuning.py fix cancel ft job route 2024-07-31 16:19:15 -07:00
test_organizations.py (feat proxy) [beta] add support for organization role based access controls (#6112) 2024-10-09 15:18:18 +05:30
test_passthrough_endpoints.py test test_basic_passthrough 2024-08-06 21:17:07 -07:00
test_ratelimit.py test(test_ratelimit.py): fix test to send below rpm 2024-04-30 19:35:21 -07:00
test_spend_logs.py Litellm ruff linting enforcement (#5992) 2024-10-01 19:44:20 -04:00
test_team_logging.py mark test_team_logging as flaky 2024-09-04 20:29:21 -07:00
test_team.py LiteLLM Minor Fixes & Improvements (10/08/2024) (#6119) 2024-10-08 21:57:03 -07:00
test_users.py LiteLLM Minor Fixes & Improvements (10/08/2024) (#6119) 2024-10-08 21:57:03 -07:00

README.MD

In total litellm runs 500+ tests Most tests are in /litellm/tests. These are just the tests for the proxy docker image, used for circle ci.