Files
mlx/mlx
Jagrit Digani 89d327075f Enabling fused attention for head dim 128 (#1899)
* Share KV smem

* Fix bfloat error

* Unroll O = S @ V loop

* Perf upgrade

* Remove commented out function

* Add -Wno-c++17-extensions flag to metal flags

* Add -Wno-c++17-extensions flag to metal extension flags
2025-02-26 10:02:06 -08:00
..
2023-11-29 10:52:08 -08:00
2025-02-13 17:10:03 -08:00
2025-02-07 15:52:22 -08:00
2024-11-18 19:17:01 -08:00
2025-02-19 20:28:13 -08:00
2025-02-13 18:46:11 -08:00
2023-11-30 11:12:53 -08:00
2024-06-12 22:06:49 -07:00
2025-02-25 06:00:53 -08:00
2025-02-07 15:52:22 -08:00
2025-01-25 01:28:03 -08:00
2024-07-25 09:36:44 -07:00
2024-12-09 11:09:02 -08:00
2024-12-09 11:09:02 -08:00
2025-02-25 11:39:36 -08:00
2025-02-13 08:44:14 -08:00
2025-02-13 08:44:14 -08:00
2025-02-13 08:44:14 -08:00
2024-12-09 11:09:02 -08:00
2024-12-09 11:09:02 -08:00
2025-01-27 22:15:01 -08:00
2025-02-07 15:52:22 -08:00