Joao Gante 4f93cc9174 fix: providing a tensor to cache_position in model.generate kwargs always crashes because of boolean test (#39300) ...

* fix: cache_position: RuntimeError: Boolean value of Tensor with more than one value is ambiguous

* test cache_position

* move test

* propagate changes

---------

Co-authored-by: Masataro Asai <guicho2.71828@gmail.com>

2025-07-30 17:30:28 +00:00

..

__init__.py

…

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

[Paged-Attention] Handle continuous batching for repetition penalty (#39457)

2025-07-22 18:13:40 +02:00

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

fix: providing a tensor to cache_position in model.generate kwargs always crashes because of boolean test (#39300)

2025-07-30 17:30:28 +00:00