Skip to content

Conversation

@gzy19990617
Copy link
Collaborator

@gzy19990617 gzy19990617 commented Sep 10, 2025

1.支持 EP Rollout 模型初始化。
2.告别 Hard Code:num_nvl_bytes 和 num_rdma_bytes 由模型参数动态计算,单机 8 卡下每卡节省 5G+ 显存。
3.引入 DeepEPBufferManager:实现DeeepEP buffer的动态申请与释放,按需分配,进一步节约显存。
4.重构部分ep.py,抽象出 DeepEPBuffer 类,代码结构更清晰、简洁(未来还需进一步优化)。

@paddle-bot
Copy link

paddle-bot bot commented Sep 10, 2025

Thanks for your contribution!

@gzy19990617 gzy19990617 changed the title [BugFix]fix tp/ep group gid [NewFeture]add ep rollout model init and update/clear ep buffer Sep 10, 2025
EmmonsCurse
EmmonsCurse previously approved these changes Sep 17, 2025
@Jiang-Jia-Jun Jiang-Jia-Jun merged commit 896e3bb into PaddlePaddle:develop Sep 17, 2025
5 of 7 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants