Nikos Karampatziakis ca59d6f77c Offloaded KV Cache (#31325) ...

* Initial implementation of OffloadedCache

* enable usage via cache_implementation

* Address feedback, add tests, remove legacy methods.

* Remove flash-attn, discover synchronization bugs, fix bugs

* Prevent usage in CPU only mode

* Add a section about offloaded KV cache to the docs

* Fix typos in docs

* Clarifications and better explanation of streams

2024-08-01 14:42:07 +02:00

..

__init__.py

[Test refactor 1/5] Per-folder tests reorganization (#15725)

2022-02-23 15:46:28 -05:00

test_activations_tf.py

TF: Add sigmoid activation function (#16819)

2022-04-19 16:13:08 +01:00

test_activations.py

Add the GeLU activation from pytorch with the tanh approximation (#21345)

2023-02-02 09:33:04 -05:00

test_add_new_model_like.py

Remove static pretrained maps from the library's internals (#29112)

2024-03-25 10:33:38 +01:00

test_audio_utils.py

Remove trust_remote_code when loading Libri Dummy (#31748)

2024-07-23 14:54:38 +08:00

test_backbone_utils.py

🚨 out_indices always a list (#30941)

2024-05-22 15:23:04 +01:00

test_cache_utils.py

Offloaded KV Cache (#31325)

2024-08-01 14:42:07 +02:00

test_chat_template_utils.py

Make tool JSON schemas consistent (#31756)

2024-07-02 20:00:42 +01:00

test_cli.py

Safetensors serialization by default (#27064)

2023-10-31 19:16:49 +01:00

test_configuration_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_convert_slow_tokenizer.py

Revert error back into warning for byte fallback conversion. (#22607)

2023-04-06 14:00:29 +02:00

test_deprecation.py

Decorators for deprecation and named arguments validation (#30799)

2024-06-10 12:35:10 +01:00

test_doc_samples.py

Skip tests properly (#31308)

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

test_dynamic_module_utils.py

Fix the regex in get_imports to support multiline try blocks and excepts with specific exception types (#23725)

2023-05-24 15:40:19 -04:00

test_feature_extraction_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_file_utils.py

Inheritance-based framework detection (#21784)

2023-02-27 15:31:55 +00:00

test_generic.py

Decorators for deprecation and named arguments validation (#30799)

2024-06-10 12:35:10 +01:00

test_hf_argparser.py

Allow for str versions of dicts based on typing (#30227)

2024-04-16 08:15:09 -04:00

test_hub_utils.py

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

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

test_image_processing_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_image_utils.py

fix: Replaced deprecated mktemp() function (#32123)

2024-07-22 14:13:39 +01:00

test_logging.py

Fix flaky test for log level (#21776)

2023-02-28 16:24:14 -05:00

test_model_card.py

Black preview (#17217)

2022-05-12 16:25:55 -04:00

test_model_output.py

Skip tests properly (#31308)

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

test_modeling_flax_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_modeling_rope_utils.py

Llama: RoPE refactor (#32135)

2024-07-23 10:42:55 +01:00

test_modeling_tf_core.py

Add tf_keras imports to prepare for Keras 3 (#28588)

2024-01-30 17:26:36 +00:00

test_modeling_tf_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_modeling_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_offline.py

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

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

test_skip_decorators.py

Update quality tooling for formatting (#21480)

2023-02-06 18:10:56 -05:00

test_tokenization_utils.py

Follow up for #31973 (#32025)

2024-07-25 16:12:23 +02:00

test_versions_utils.py

improve dev setup comments and hints (#28495)

2024-01-15 18:36:40 +00:00

tiny_model_summary.json

Update tests/utils/tiny_model_summary.json (#29941)

2024-04-03 09:25:01 +02:00