Manuel de Prada Corral
c338fd43b0
[cache refactor] Move all the caching logic to a per-layer approach (#39106)
* Squash for refactor: Replace monolithic cache classes with modular LayeredCache (#38077)
- Introduces CacheLayer and Cache base classes
- Ports Static, Dynamic, Offloaded, Quantized, Hybrid, etc. to use layers
- Implements method/attr dispatch across layers to reduce boilerplate
- Adds CacheProcessor hooks for offloading, quantization, etc.
- Updates and passes tests
* fix quantized, add tests
* remove CacheProcessorList
* raushan review, arthur review
* joao review: minor things
* remove cache configs, make CacheLayer a mixin (joaos review)
* back to storage inside Cache()
* remove cachebase for decorator
* no more __getattr__
* fix tests
* joaos review except docs
* fix ast deprecations for python 3.14: replace node.n by node.value and use `ast.Constant`
More verbose exceptions in `fix_docstring` on docstring formatting issues.
* Revert "back to storage inside Cache()"
This reverts commit 27916bc2737806bf849ce2148cb1e66d59573913.
* cyril review
* simplify cache export
* fix lfm2 cache
* HybridChunked to layer
* BC proxy object for cache.key_cache[i]=...
* reorder classes
* bfff come on LFM2
* better tests for hybrid and hybridChunked
* complete coverage for hybrid chunked caches (prefill chunking)
* reimplementing HybridChunked
* cyril review
* fix ci
* docs for cache refactor
* docs
* oopsie
* oopsie
* fix after merge
* cyril review
* arthur review
* opsie
* fix lfm2
* opsie2
2025-07-22 16:10:25 +02:00
..
2025-05-09 15:26:27 +02:00
2022-02-23 15:46:28 -05:00
2025-01-24 16:55:28 +01:00
2025-06-26 16:25:00 +01:00
2025-07-08 17:06:12 +02:00
2025-05-08 17:46:07 -04:00
2024-05-22 15:23:04 +01:00
2025-07-22 16:10:25 +02:00
2025-04-08 14:12:08 +02:00
2025-04-30 12:15:43 +01:00
2025-07-18 13:41:54 +02:00
2023-04-06 14:00:29 +02:00
2025-05-09 08:45:01 +02:00
2025-06-25 17:29:10 +00:00
2023-05-24 15:40:19 -04:00
2025-06-13 16:14:58 +02:00
2025-04-08 14:12:08 +02:00
2025-06-26 16:25:00 +01:00
2025-07-05 11:34:28 +02:00
2025-07-17 15:47:31 +00:00
2025-04-22 11:38:10 +02:00
2025-04-08 14:12:08 +02:00
2025-05-12 11:55:51 +02:00
2025-07-17 13:21:59 +00:00
2025-03-17 16:09:09 +01:00
2023-02-28 16:24:14 -05:00
2025-07-10 18:53:40 +02:00
2025-06-13 11:07:09 +00:00
2025-04-18 16:45:54 +02:00
2025-04-08 14:12:08 +02:00
2025-07-10 05:18:44 +00:00
2025-07-18 13:41:54 +02:00
2025-04-08 14:12:08 +02:00
2025-05-09 08:45:01 +02:00
2025-04-08 14:12:08 +02:00
2025-04-10 20:54:21 +02:00
2025-06-25 08:23:37 +00:00
2024-10-31 15:48:11 -04:00