Wang, Yi
9323d0873c
use the enable_gqa param in torch.nn.functional.scaled_dot_product_at… (#39412)
* use the enable_gqa param in torch.nn.functional.scaled_dot_product_attention
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* ci failure fix
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* add check
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix ci failure
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* refine code, extend to cuda
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* refine code
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* fix review comments
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
* refine the PR
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Cyril Vallez <cyril.vallez@huggingface.co>
2025-07-21 14:46:43 +02:00
..
2025-05-09 15:26:27 +02:00
2022-02-23 15:46:28 -05:00
2025-01-24 16:55:28 +01:00
2025-06-26 16:25:00 +01:00
2025-07-08 17:06:12 +02:00
2025-05-08 17:46:07 -04:00
2024-05-22 15:23:04 +01:00
2025-07-21 14:46:43 +02:00
2025-04-08 14:12:08 +02:00
2025-04-30 12:15:43 +01:00
2025-07-18 13:41:54 +02:00
2023-04-06 14:00:29 +02:00
2025-05-09 08:45:01 +02:00
2025-06-25 17:29:10 +00:00
2023-05-24 15:40:19 -04:00
2025-06-13 16:14:58 +02:00
2025-04-08 14:12:08 +02:00
2025-06-26 16:25:00 +01:00
2025-07-05 11:34:28 +02:00
2025-07-17 15:47:31 +00:00
2025-04-22 11:38:10 +02:00
2025-04-08 14:12:08 +02:00
2025-05-12 11:55:51 +02:00
2025-07-17 13:21:59 +00:00
2025-03-17 16:09:09 +01:00
2023-02-28 16:24:14 -05:00
2025-07-10 18:53:40 +02:00
2025-06-13 11:07:09 +00:00
2025-04-18 16:45:54 +02:00
2025-04-08 14:12:08 +02:00
2025-07-10 05:18:44 +00:00
2025-07-18 13:41:54 +02:00
2025-04-08 14:12:08 +02:00
2025-05-09 08:45:01 +02:00
2025-04-08 14:12:08 +02:00
2025-04-10 20:54:21 +02:00
2025-06-25 08:23:37 +00:00
2024-10-31 15:48:11 -04:00