mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-30 06:43:27 +00:00
321be01877
* fix(caching): write the response-cache SET to Redis at once instead of on the post-call batch The post-call Redis batch only goes out after every success callback finishes or the 1s deadline, so an identical request sent right after the first response missed the cache and went to the provider again. Response-cache writes go straight to Redis again, the counters, rate limits, TPM and slot releases keep riding the post-call batch Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(caching): re-export DualCache explicitly instead of through a noqa Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(caching): keep the DualCache re-export as a reasoned noqa for the strict ruff gate Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| test_azure_blob_cache.py | ||
| test_cache_preset_key.py | ||
| test_caching.py | ||
| test_caching_handler.py | ||
| test_check_and_fix_namespace_none_guard.py | ||
| test_disk_cache.py | ||
| test_dual_cache.py | ||
| test_embedding_router.py | ||
| test_evicted_client_closer.py | ||
| test_gcs_cache.py | ||
| test_in_memory_cache.py | ||
| test_llm_caching_handler.py | ||
| test_llm_client_cache_e2e.py | ||
| test_qdrant_semantic_cache.py | ||
| test_redis_batch.py | ||
| test_redis_cache.py | ||
| test_redis_cluster_cache.py | ||
| test_redis_cluster_node_isolation.py | ||
| test_redis_connection_pool.py | ||
| test_redis_semantic_cache.py | ||
| test_request_redis_batch_post_call.py | ||
| test_request_redis_batch_pre_call.py | ||
| test_responses_stream_cache_keys.py | ||
| test_s3_cache.py | ||
| test_unit_test_caching.py | ||
| test_valkey_semantic_cache.py | ||