[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

docs/source/en/internal/generation_utils.md

@@ -356,66 +356,93 @@ A [`Constraint`] can be used to force the generation to include specific tokens
 
 ## Caches
 
-[[autodoc]] Cache
-    - update
-
-[[autodoc]] CacheConfig
-	- update
-
-[[autodoc]] QuantizedCacheConfig
-	- validate
-
-[[autodoc]] DynamicCache
+[[autodoc]] CacheLayerMixin
     - update
     - get_seq_length
+    - get_mask_sizes
+    - get_max_cache_shape
+    - reset
     - reorder_cache
+
+[[autodoc]] DynamicLayer
+    - update
+    - crop
+    - batch_repeat_interleave
+    - batch_select_indices
+
+[[autodoc]] StaticLayer
+    - update
+
+[[autodoc]] SlidingWindowLayer
+    - update
+
+[[autodoc]] CacheProcessor
+    - pre_update
+    - post_update
+
+[[autodoc]] OffloadedCacheProcessor
+    - pre_update
+
+[[autodoc]] QuantizedCacheProcessor
+    - post_update
+
+[[autodoc]] QuantoQuantizedCacheProcessor
+    - post_update
+
+[[autodoc]] HQQQuantizedCacheProcessor
+    - post_update
+
+[[autodoc]] Cache
+    - update
+    - get_seq_length
+    - get_mask_sizes
+    - get_max_cache_shape
+    - reset
+    - reorder_cache
+    - crop
+    - batch_repeat_interleave
+    - batch_select_indices
+
+[[autodoc]] DynamicCache
     - to_legacy_cache
     - from_legacy_cache
 
 [[autodoc]] QuantizedCache
-    - update
-    - get_seq_length
 
 [[autodoc]] QuantoQuantizedCache
 
+[[autodoc]] QuantoQuantizedCacheProcessor
+
 [[autodoc]] HQQQuantizedCache
 
+[[autodoc]] HQQQuantizedCacheProcessor
+
 [[autodoc]] OffloadedCache
-    - update
-    - prefetch_layer
-    - evict_previous_layer
 
 [[autodoc]] StaticCache
-    - update
-    - get_seq_length
-    - reset
 
 [[autodoc]] OffloadedStaticCache
-    - update
-    - get_seq_length
-    - reset
 
 [[autodoc]] HybridCache
-    - update
-    - get_seq_length
-    - reset
+
+[[autodoc]] HybridChunkedCache
 
 [[autodoc]] SlidingWindowCache
-    - update
-    - reset
 
 [[autodoc]] EncoderDecoderCache
-    - get_seq_length
     - to_legacy_cache
     - from_legacy_cache
-    - reset
-    - reorder_cache
 
 [[autodoc]] MambaCache
     - update_conv_state
     - update_ssm_state
     - reset
 
+[[autodoc]] CacheConfig
+
+[[autodoc]] QuantizedCacheConfig
+
+
 ## Watermark Utils
 
 [[autodoc]] WatermarkingConfig