Skip to content

Conversation

@lizexu123
Copy link
Collaborator

@lizexu123 lizexu123 commented Aug 14, 2025

将rebuild_padding输入cum_offsets替换成cu_seqlens_q,减少了计算量

@paddle-bot
Copy link

paddle-bot bot commented Aug 14, 2025

Thanks for your contribution!

freeliuzc
freeliuzc previously approved these changes Aug 18, 2025
@zhoutianzi666 zhoutianzi666 merged commit 32b3962 into PaddlePaddle:develop Aug 18, 2025
13 of 15 checks passed
littledgg pushed a commit to littledgg/FastDeploy that referenced this pull request Sep 8, 2025
Jiang-Jia-Jun pushed a commit that referenced this pull request Oct 9, 2025
* success run ngram

* Revert "[Code Simplification] remove cum_offsets (#3410)"

This reverts commit 32b3962.

* success run ngram5 tp4 42bs

* success run ngram5 tp4 42bs

* mtp draft commit

* add decorator for target model

* enable draft model in cudagraph v0.5

* revert revrt cum_offset

* enable target model in cudagraph v0.9 And clean debug code

* Revert "success run ngram"

This reverts commit 8351e83.

* add reverted code

* enable target model in cudagraph v0.9

* solve comment

* fix bid < 0

* Enable Target Model Padding And Draft Model in cudagraph

* solve problem

* delete rebuild padding debug note

* fast compile

* Add capture list for mtp

* success run 256 tp1 mtp

* Enable Lite TP2 Bsz256

* realy enable tp2 bsz 256

* fix problem

* Solve problem for Draft model in cudagraph

* Solve comment

* replace emptytensor as zeros

* Solve comments

* Revert "fast compile"

This reverts commit 834639a.

* fix bug

* fix merge bug

* fix typo

* fix bug

---------

Co-authored-by: lizexu <[email protected]>
Co-authored-by: littledgg <[email protected]>
Co-authored-by: zeroRains <[email protected]>
Co-authored-by: gongshaotian <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants