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

..

internal

[cache refactor] Move all the caching logic to a per-layer approach (#39106)

2025-07-22 16:10:25 +02:00

main_classes

[agents] remove agents 🧹 (#37368)

2025-04-11 18:42:37 +01:00

model_doc

Simplify and update trl examples (#38772)

2025-06-13 12:03:49 +00:00

quantization

🌐 [i18n-KO] Translated quark.md to Korean (#39268)

2025-07-09 09:29:51 -07:00

tasks

No more Tuple, List, Dict (#38797)

2025-06-17 19:37:18 +01:00

_config.py

[#29174] ImportError Fix: Trainer with PyTorch requires accelerate>=0.20.1 Fix (#29888)

2024-04-08 14:21:16 +01:00

_toctree.yml

🌐 [i18n-KO] Translated perf_infer_gpu_multi.md to Korean (#39441)

2025-07-21 09:14:15 -07:00

accelerate.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

add_new_model.md

Transformers cli clean command (#37657)

2025-04-30 12:15:43 +01:00

add_new_pipeline.md

add push_to_hub to pipeline (#29172)

2024-04-16 15:34:04 +01:00

attention.md

[Docs] Fix broken links and syntax issues (#28918)

2024-02-08 14:13:35 -08:00

autoclass_tutorial.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

bertology.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

big_models.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

chat_templating.md

🌐 [i18n-KO] Translated chat_templating.md to Korean (#32362)

2024-08-07 11:25:19 -07:00

community.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

contributing.md

Transformers cli clean command (#37657)

2025-04-30 12:15:43 +01:00

conversations.md

🌐 [i18n-KO] Translated conversations.md to Korean (#32468)

2024-08-27 09:25:41 -07:00

create_a_model.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

custom_models.md

No more Tuple, List, Dict (#38797)

2025-06-17 19:37:18 +01:00

debugging.md

🌐 [i18n-KO] Translated debugging.md to Korean (#26246)

2023-09-27 13:47:44 -07:00

deepspeed.md

Transformers cli clean command (#37657)

2025-04-30 12:15:43 +01:00

fast_tokenizers.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

fsdp.md

🌐 [i18n-KO] Translated fsdp.md to Korean (#32261)

2024-08-08 09:40:03 -07:00

generation_strategies.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

gguf.md

Fixed broken links (#37466)

2025-04-14 14:16:07 +01:00

glossary.md

Add Korean translation for glossary.md (#38804)

2025-07-07 09:12:55 -07:00

gpu_selection.md

🌐 [i18n-KO] Translated gpu_selection.md to Korean (#36757)

2025-05-01 08:44:12 -07:00

hpo_train.md

Trainer - deprecate tokenizer for processing_class (#32385)

2024-10-02 14:08:46 +01:00

in_translation.md

Migrate doc files to Markdown. (#24376)

2023-06-20 18:07:47 -04:00

index.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

installation.md

docs: HUGGINGFACE_HUB_CACHE -> HF_HUB_CACHE (#34904)

2024-11-26 09:37:18 -08:00

llm_optims.md

[CI] green llama tests (#37244)

2025-04-03 14:15:53 +01:00

llm_tutorial_optimization.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

llm_tutorial.md

Update Korean tutorial for using LLMs, and refactor the nested conditional statements in hr_argparser.py (#27489)

2023-11-20 17:14:23 +00:00

model_memory_anatomy.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

model_sharing.md

[docs] update not-working model revision (#34682)

2024-11-11 07:09:31 -08:00

model_summary.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

modular_transformers.md

🌐 [i18n-KO] Translated modular_transformers.md to Korean (#33772)

2024-10-08 18:30:41 -07:00

multilingual.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

pad_truncation.md

[Docs] Fix backticks in inline code and documentation links (#28875)

2024-02-06 11:15:44 -08:00

peft.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

perf_hardware.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

perf_infer_cpu.md

🌐 [i18n-KO] Translated perf_infer_cpu.md to Korean (#24920)

2023-07-25 16:04:14 +02:00

perf_infer_gpu_multi.md

🌐 [i18n-KO] Translated perf_infer_gpu_multi.md to Korean (#39441)

2025-07-21 09:14:15 -07:00

perf_infer_gpu_one.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

perf_train_cpu_many.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

perf_train_cpu.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

perf_train_gpu_many.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

perf_train_special.md

🌐 [i18n-KO] Translated perf_train_special.md to Korean (#34590)

2024-11-04 09:41:44 -08:00

perf_train_tpu_tf.md

🌐 [i18n-KO] Translated perf_train_tpu_tf.md to Korean (#25433)

2023-08-18 23:08:34 +02:00

performance.md

🌐[i18n-KO] Translated performance.md to Korean (#24883)

2023-07-24 09:23:34 -04:00

perplexity.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

philosophy.md

[docs] fixed links with 404 (#27327)

2023-11-06 19:45:03 +00:00

pipeline_tutorial.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

pipeline_webserver.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

pr_checks.md

[i18n-KO] Translated docs: ko: pr_checks.md to Korean (#24987)

2023-08-17 08:03:17 +02:00

preprocessing.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

quicktour.md

Fix typos in translated quicktour docs (#35302)

2024-12-17 09:32:00 -08:00

run_scripts.md

Remove research projects (#36645)

2025-03-11 13:47:38 +00:00

sagemaker.md

[docs] fixed links with 404 (#27327)

2023-11-06 19:45:03 +00:00

serialization.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

serving.md

🌐 [i18n-KO] Translated gpu_selection.md to Korean (#36757)

2025-05-01 08:44:12 -07:00

task_summary.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

tasks_explained.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

testing.md

[tests] remove TF tests (uses of require_tf) (#38944)

2025-06-25 17:29:10 +00:00

tf_xla.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

tflite.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

tokenizer_summary.md

Use HF papers (#38184)

2025-06-13 11:07:09 +00:00

torchscript.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00

trainer.md

Simplify and update trl examples (#38772)

2025-06-13 12:03:49 +00:00

training.md

🚨🚨🚨Deprecate evaluation_strategy to eval_strategy🚨🚨🚨 (#30190)

2024-04-18 12:49:43 -04:00

troubleshooting.md

Update all references to canonical models (#29001)

2024-02-16 08:16:58 +01:00