Files
HuggingFace_transformer/docs/source/en/model_doc
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
..
2024-04-26 16:23:44 +01:00
2023-11-06 19:45:03 +00:00
2023-11-10 13:49:10 +00:00
2024-04-16 11:58:55 +02:00
2024-03-15 14:29:11 +01:00
2024-04-18 15:18:52 +02:00
2023-11-23 17:44:08 +00:00
2023-11-23 17:44:08 +00:00
2024-03-12 10:16:21 +00:00
2024-02-21 14:21:28 +01:00
2024-04-15 17:03:03 +01:00
2024-04-18 11:04:02 +02:00
2023-10-30 21:42:19 +01:00
2023-12-20 14:25:07 +05:30
2024-04-24 10:11:19 +02:00
2024-04-22 10:41:03 +01:00
2024-04-17 17:59:07 +02:00
2024-02-19 15:22:29 +01:00
2024-02-19 15:22:29 +01:00
2024-04-24 17:32:09 +02:00
2024-03-13 19:05:20 +00:00
2024-02-23 10:43:31 +01:00
2023-11-06 19:45:03 +00:00
2023-07-13 11:46:54 -04:00
2024-04-19 21:03:07 +02:00
2024-04-22 10:41:03 +01:00
2024-02-19 15:22:29 +01:00
2024-04-19 18:31:43 +01:00
2023-11-06 19:45:03 +00:00
2023-11-23 17:02:16 +00:00
2023-12-15 20:16:47 +01:00
2024-02-19 15:22:29 +01:00