Optimizing the performance of think length limit using custom operators - #4279
Merged
Jiang-Jia-Jun merged 38 commits intoOct 20, 2025
Merged
Conversation
|
Thanks for your contribution! |
yuanlehome
marked this pull request as draft
September 26, 2025 05:47
yuanlehome
force-pushed
the
upgrade_limit_think_length
branch
from
October 13, 2025 03:19
3bad98a to
73384a6
Compare
yuanlehome
marked this pull request as ready for review
October 13, 2025 08:07
yuanlehome
force-pushed
the
upgrade_limit_think_length
branch
from
October 14, 2025 10:24
62dd5da to
6f1f082
Compare
…ehome/FastDeploy into upgrade_limit_think_length
…into upgrade_limit_think_length
…into upgrade_limit_think_length
K11OntheBoat
previously approved these changes
Oct 16, 2025
K11OntheBoat
left a comment
K11OntheBoat
left a comment
Collaborator
There was a problem hiding this comment.
LGTM.
得check一下PD分离下，max_think_len=1的极端情况
可以参考这个PR: #4433
这个PR的一些改动修复了极端情况的Bug.
| __global__ void limit_thinking_content_length_kernel_v2( | ||
| int64_t *next_tokens, | ||
| const int *max_think_lens, | ||
| const int64_t *step_idx, // step_idx 不再需要被修改，改为 const |
…into upgrade_limit_think_length
…into upgrade_limit_think_length
…into upgrade_limit_think_length
…into upgrade_limit_think_length
yuanlehome
force-pushed
the
upgrade_limit_think_length
branch
from
October 20, 2025 04:02
96de19f to
849eaa6
Compare
…into upgrade_limit_think_length
…into upgrade_limit_think_length
…into upgrade_limit_think_length
xiaoguoguo626807
pushed a commit
to xiaoguoguo626807/FastDeploy
that referenced
this pull request
May 7, 2026
…rs (PaddlePaddle#4279) * delete impl * delete min_length&max_length * support limit thinking content strategy * fix * fix * fix * update * fix set_value_by_flags_and_idx * fix * fix * fix * fix * update * fix * fix * fix typo * fix ci * fix * fix * support mtp * fix * fix * update * update
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Changed:
</think> for ernie4_5_vl, \n</think>\n\n for ernie_x1，分别实现了两个自定义算子算子单测：#4510
XPU实现：#4539