PaddlePaddle
split seq_len to improve mmha perf
PR Category
Inference
PR Types
Others
Description
split seq_len to improve mmha perf, with postProcessKernel and mmhaKernel optimazation
P-card-71501
你的PR提交成功，感谢你对开源项目的贡献! 请关注后续CI自动化测试结果，详情请参考Paddle-CI手册。 Your PR has been submitted. Thanks for your contribution! Please wait for the result of CI firstly. See Paddle CI Manual for details.
![paddle-bot[bot] avatar](https://avatars.githubusercontent.com/in/216376?v=4 "Published by a pub.dev verified publisher"){kind=small}
❌ The PR is not created using PR's template. You can refer to this Demo. Please use PR's template, it helps save our maintainers' time so that more developers get helped.
Sorry to inform you that fc6fda8's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.
![paddle-ci-bot[bot] avatar](https://avatars.githubusercontent.com/u/66985341?v=4 "Published by a pub.dev verified publisher"){kind=small}
Sorry to inform you that c24bb70's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually.