Sanchit Gandhi a9701953ff [whisper] static kv cache (#31166) ...

* make work with cache abstraction

* correct for static cache

* hacks for compile

* make fast

* fix

* fix pos ids

* generate

* fix sdpa

* fix sdpa cache pos

* fix fa2

* clean fa2

* integrate cache into generate

* make style

* copies

* more copies

* update eager

* update sdpa

* update fa2

* simplify

* use cache pos

* always compute cross-cache for debug

* avoid recompiles
Co-authored-by: Arthur Zucker <arthur@huggingface.co>

* fix fix

* fix fix fix

* more fix

* try encoder-decoder cache (too messy)

* revert encoder-decoder cache

* check cross-attn cache

* use enc-dec dataclass

* use richer enc-dec dataclass

* clean-up

* revert static cache changes

* small fixes

* revert to cpu flag

* fix copies

* add static slow test

* past k/v docstring

* more docstrings

* cache_position docstrings

* add to docs

* add enc-dec cache to docs

* make style

* fix after rebase

* fix beam

* style

* fix generation strategies

* fix most decoder-only tests

* style

* skip test

* more clean up

* small docstrings

* Apply suggestions from code review

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>

* add todo

* only crop self-attn

* check cache in mixin

* style

* fix re-compile after rebase

* move `is_updated` logic to enc-dec wrapper

* revert back

* revert cache back

* finalise design

* fix

* fix fix

* style

* Update src/transformers/cache_utils.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* deprecate

* updates

* final updates

* style

* style

---------

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

2024-07-02 13:24:15 +01:00

..

internal

[whisper] static kv cache (#31166)

2024-07-02 13:24:15 +01:00

main_classes

Fast image processor (#28847)

2024-06-11 15:47:38 +01:00

model_doc

[whisper] static kv cache (#31166)

2024-07-02 13:24:15 +01:00

quantization

Docs / AQLM: Clarify torch.compile support for AQLM (#31473)

2024-06-19 11:26:25 +02:00

tasks

Update mask_generation.md (#31543)

2024-06-23 20:27:21 +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

_redirects.yml

Docs / Quantization: Redirect deleted page (#31063)

2024-05-28 18:29:22 +02:00

_toctree.yml

Fix post gemma merge (#31660)

2024-06-27 17:51:42 +02:00

accelerate.md

Fix typos (#25936)

2023-09-04 11:15:12 +01:00

add_new_model.md

Remove add-new-model in favor of add-new-model-like (#30424)

2024-04-24 09:38:18 +02:00

add_new_pipeline.md

add push_to_hub to pipeline (#29172)

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

agents.md

Add streaming, various fixes (#30838)

2024-05-31 14:16:23 +02:00

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

benchmarks.md

Update all references to canonical models (#29001)

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

bertology.md

Migrate doc files to Markdown. (#24376)

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

big_models.md

[docs] Big model loading (#29920)

2024-04-01 18:47:32 -07:00

chat_templating.md

Update chat template docs and bump Jinja version (#31455)

2024-06-18 14:16:30 +01:00

community.md

Update all references to canonical models (#29001)

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

contributing.md

…

conversations.md

Add sidebar tutorial for chat models (#30401)

2024-04-25 19:38:48 +01:00

create_a_model.md

Enable HF pretrained backbones (#31145)

2024-06-06 22:02:38 +01:00

custom_models.md

[Docs] Add language identifiers to fenced code blocks (#28955)

2024-02-12 10:48:31 -08:00

debugging.md

[Docs] Fix spelling and grammar mistakes (#28825)

2024-02-02 08:45:00 +01:00

deepspeed.md

Rename torch.run to torchrun (#30405)

2024-04-23 09:04:17 -07:00

fast_tokenizers.md

Migrate doc files to Markdown. (#24376)

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

fsdp.md

[docs] Trainer docs (#28145)

2023-12-20 10:37:23 -08:00

generation_strategies.md

Quantized KV Cache (#30483)

2024-05-23 17:25:20 +05:00

gguf.md

Add Qwen2 GGUF loading support (#31175)

2024-06-03 14:55:10 +01:00

glossary.md

Update all references to canonical models (#29001)

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

hpo_train.md

Remove-auth-token (#27060)

2023-11-13 14:20:54 +01:00

index.md

Add gemma 2 (#31659)

2024-06-27 17:36:19 +02:00

installation.md

Use HF_HUB_OFFLINE + fix has_file in offline mode (#31016)

2024-05-29 11:55:43 +01:00

llm_optims.md

Add torch.compile for Mistral (#30642)

2024-05-20 16:27:24 +02:00

llm_tutorial_optimization.md

F.scaled_dot_product_attention support (#26572)

2023-12-09 05:38:14 +09:00

llm_tutorial.md

Generate: update links on LLM tutorial doc (#30550)

2024-04-30 18:14:12 +01:00

model_memory_anatomy.md

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

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

model_sharing.md

Update all references to canonical models (#29001)

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

model_summary.md

model_summary.md - Restore link to Harvard's Annotated Transformer. (#29702)

2024-03-23 18:29:39 -07:00

multilingual.md

Update all references to canonical models (#29001)

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

notebooks.md

…

pad_truncation.md

[Doc] Spanish translation of pad_truncation.md (#27890)

2023-12-08 10:32:18 -08:00

peft.md

Docs / Quantization: Replace all occurences of load_in_8bit with bnb config (#31136)

2024-05-30 16:47:35 +02:00

perf_hardware.md

Update all references to canonical models (#29001)

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

perf_infer_cpu.md

[Docs] Fix spelling and grammar mistakes (#28825)

2024-02-02 08:45:00 +01:00

perf_infer_gpu_one.md

Fix post gemma merge (#31660)

2024-06-27 17:51:42 +02:00

perf_torch_compile.md

docs: fix style (#31340)

2024-06-10 09:53:25 +01:00

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

Update perf_train_gpu_many.md (#31451)

2024-06-18 11:00:26 -07:00

perf_train_gpu_one.md

Fix minor typo: softare => software (#29602)

2024-03-12 10:39:56 +00:00

perf_train_special.md

Update all references to canonical models (#29001)

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

perf_train_tpu_tf.md

Migrate doc files to Markdown. (#24376)

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

performance.md

[docs] Update CPU/GPU inference docs (#26881)

2023-10-31 09:44:51 -07:00

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

More fixes for doctest (#30265)

2024-04-16 11:58:55 +02:00

pipeline_webserver.md

Update all references to canonical models (#29001)

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

pr_checks.md

[Docs] Fix spelling and grammar mistakes (#28825)

2024-02-02 08:45:00 +01:00

preprocessing.md

Update all references to canonical models (#29001)

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

quicktour.md

docs: fix broken link (#31370)

2024-06-12 11:33:00 +01:00

run_scripts.md

Fix broken link to Transformers notebooks (#30512)

2024-04-29 10:57:51 +01:00

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

task_summary.md

More fixes for doctest (#30265)

2024-04-16 11:58:55 +02:00

tasks_explained.md

[docs] Spanish translation of tasks_explained.md (#29224)

2024-02-26 08:18:15 -08:00

testing.md

Skip tests properly (#31308)

2024-06-26 21:59:08 +01:00

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

[docs] Spanish translation of tokenizer_summary.md (#31154)

2024-06-03 16:52:23 -07:00

torchscript.md

Update all references to canonical models (#29001)

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

trainer.md

FEAT / Trainer: LOMO optimizer support (#30178)

2024-05-21 10:16:37 +02:00

training.md

Added the necessay import of module (#30804)

2024-05-14 18:45:06 +01:00

troubleshooting.md

Update all references to canonical models (#29001)

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