Raushan Turganbay 8d6259b0b8 [refactor] set attention implementation (#38974) ...

* update

* fix some tests

* init from config, changes it in-place, add deepcopy in tests

* fix modernbert

* don't delete thsi config attr

* update

* style and copies

* skip tests in generation

* fix style

* accidentally removed flash-attn-3, revert

* docs

* forgot about flags set to False

* fix copies

* address a few comments

* fix copies

* custom code BC

2025-07-15 09:34:06 +02:00

..

__init__.py

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

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

test_beam_constraints.py

Use Python 3.9 syntax in tests (#37343)

2025-04-08 14:12:08 +02:00

test_beam_search.py

Use Python 3.9 syntax in tests (#37343)

2025-04-08 14:12:08 +02:00

test_candidate_generator.py

prune LM Head for USD (#36695)

2025-04-08 16:44:10 +01:00

test_configuration_utils.py

🚨🚨🚨 [pipelines] update defaults in pipelines that can generate (#38129)

2025-05-19 18:02:06 +01:00

test_flash_attention_parity.py

Support for Flash Attention 3 (#38972)

2025-06-25 14:39:27 +02:00

test_fsdp.py

enable generation fsdp/utils cases on XPU (#38009)

2025-05-09 20:52:41 +00:00

test_logits_process.py

Add Dia model (#38405)

2025-06-26 11:04:23 +00:00

test_paged_attention.py

enable more test cases on xpu (#38572)

2025-06-06 09:29:51 +02:00

test_stopping_criteria.py

Use Python 3.9 syntax in tests (#37343)

2025-04-08 14:12:08 +02:00

test_streamers.py

Use Python 3.9 syntax in tests (#37343)

2025-04-08 14:12:08 +02:00

test_utils.py

[refactor] set attention implementation (#38974)

2025-07-15 09:34:06 +02:00