scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91

docs(cache): align native cache follow-up scope

Browse source
This commit is contained in:
Yujong Lee 2026-09-21 07:56:58 -07:00
parent cc8cadebb4
commit 9783b7a377
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm-rust/crates/cache-response/README.md
View file

@ -52,4 +52,4 @@ Verify typed values, TTL precedence, missing entries, serialization failures, na
Public SDK, Router, and proxy activation still need constructor parity, stream replay, embedding partial-batch integration, response reconstruction, callback scheduling, and failure-policy integration. This foundation does not switch those request paths
Redis cluster, disk, cloud stores, dual caching, and semantic caching remain follow-ups. Atomic counters, affinity claims, reservations, queues, and pubsub need explicit capabilities owned by their consuming features. Adding a cache backend does not establish those guarantees
Redis cluster, disk, cloud stores, and semantic caching remain follow-ups. The generic dual cache now provides L2-first counters and atomic affinity claims with local fallback, but public Router integration remains follow-up work. Reservations, queues, and pubsub still need explicit capabilities owned by their consuming features. Adding a cache backend does not establish those guarantees