Files
HuggingFace_transformer/tests/models
JB (Don) dfa7b580e9 [BERT] Add support for sdpa (#28802)
* Adding SDPA support for BERT

* Using the proper input name for testing model input in inference()

* Adding documentation for SDPA in BERT model page

* Use the stable link for the documentation

* Adding a gate to only call .contiguous() for torch < 2.2.0

* Additions and fixes to the documentation

* Minor updates to documentation

* Adding extra requirements needed for the contiguous() bug

* Adding "Adapted from" in plcae of the "Copied from"

* Add benchmark speedup tables to the documentation

* Minor fixes to the documentation

* Use ClapText as a replacemenet for Bert in the Copied-From

* Some more fixes for the fix-copies references

* Overriding the test_eager_matches_sdpa_generate in bert tests to not load with low_cpu_mem_usage

[test all]

* Undo changes to separate test

* Refactored SDPA self attention code for KV projections

* Change use_sdpa to attn_implementation

* Fix test_sdpa_can_dispatch_on_flash by preparing input (required for MultipleChoice models)
2024-04-26 16:23:44 +01:00
..
2024-04-05 17:49:46 +02:00
2024-04-01 07:51:00 +00:00
2024-04-26 16:23:44 +01:00
2024-04-18 15:18:52 +02:00
2024-04-22 17:11:13 +01:00
2024-04-01 07:51:00 +00:00
2023-08-02 20:22:36 +02:00
2024-04-15 17:03:03 +01:00
2023-08-02 20:22:36 +02:00
2024-04-17 17:59:07 +02:00
2024-04-24 17:32:09 +02:00
2023-09-05 10:12:25 +02:00
2023-09-05 10:12:25 +02:00
2024-04-01 07:51:00 +00:00
2024-04-19 18:31:43 +01:00
2023-08-02 20:22:36 +02:00
2024-01-11 16:18:27 +01:00
2024-03-20 15:51:12 +00:00
2024-01-11 16:18:27 +01:00