Commit Graph

2 Commits (4f28cb43c0c2afbc970b9f0f300e7aa28e39bd2e)

Author SHA1 Message Date
Jianghai c647e00e3c
[Inference]Add fused rotary kernel and get cos cache kernel (#5302)
* add fused rotary and get cos cache func

* staged

* fix bugs

* fix bugs
2024-01-24 16:20:42 +08:00
Jianghai fded91d049 [Inference] Kernel: no pad rotary embedding (#5252)
* fix bugs

* comment

* use more accurate atol

* fix
2024-01-11 13:46:14 +00:00