transformers/tests
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
..
agents Agents: Improve python interpreter (#31409) 2024-06-18 11:55:36 +02:00
benchmark
bettertransformer
deepspeed Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
extended Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
fixtures
fsdp Llama et al. / FSDP : Fix breaking change in 4.40 for FSDP (#31161) 2024-06-26 14:50:08 +01:00
generation [whisper] static kv cache (#31166) 2024-07-02 13:24:15 +01:00
models [whisper] static kv cache (#31166) 2024-07-02 13:24:15 +01:00
optimization fix get_scheduler when name is warmup_stable_decay (#31128) 2024-05-30 15:25:43 +01:00
peft_integration
pipelines Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
quantization Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
repo_utils
sagemaker Pass datasets trust_remote_code (#31406) 2024-06-17 17:29:13 +01:00
tokenization Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
trainer add gather_use_object arguments (#31514) 2024-06-28 13:50:27 +01:00
utils Move some test files (tets/test_xxx_utils.py) to tests/utils (#31730) 2024-07-02 13:46:03 +02:00
__init__.py
test_backbone_common.py
test_configuration_common.py Move some test files (tets/test_xxx_utils.py) to tests/utils (#31730) 2024-07-02 13:46:03 +02:00
test_feature_extraction_common.py
test_image_processing_common.py Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
test_image_transforms.py fix: center_crop occasionally outputs off-by-one dimension matrix (#30934) 2024-05-21 13:56:52 +01:00
test_modeling_common.py Move some test files (tets/test_xxx_utils.py) to tests/utils (#31730) 2024-07-02 13:46:03 +02:00
test_modeling_flax_common.py add sdpa to ViT [follow up of #29325] (#30555) 2024-05-16 10:56:11 +01:00
test_modeling_tf_common.py
test_pipeline_mixin.py Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00
test_processing_common.py add initial design for uniform processors + align model (#31197) 2024-06-13 16:27:16 +02:00
test_sequence_feature_extraction_common.py
test_tokenization_common.py Skip tests properly (#31308) 2024-06-26 21:59:08 +01:00