Skip to content

Conversation

yuanlehome
Copy link
Collaborator

@yuanlehome yuanlehome commented Sep 25, 2025

Changed:

  1. 修复模型注册机制,原本category是没有生效的,增加is_reasoning_model判断函数(暂未用到)
  2. 删除原本通过MultimodalRegistry注册多模模型的方式
  3. 删除非nv gpu硬件的思考长度裁剪逻辑代码(原本也没有生效和验证过,后续需要通过自定义算子的形式支持)
  4. 修改common_engine.py里的cfg->fd_config,便于阅读
  5. 支持nv gpu下的思考长度裁剪功能,通过环境变量FD_LIMIT_THINKING_CONTENT_TRUNCATE_STR来指定用于截断思考的插入字符串,</think> for ernie4_5_vl, \n</think>\n\n for ernie_x1,分别实现了两个自定义算子
  6. 支持MTP下的思考长度裁剪
  7. 其他一些代码优化

Copy link

paddle-bot bot commented Sep 25, 2025

Thanks for your contribution!

@yuanlehome yuanlehome marked this pull request as draft September 26, 2025 05:47
@yuanlehome yuanlehome force-pushed the upgrade_limit_think_length branch from 3bad98a to 73384a6 Compare October 13, 2025 03:19
@yuanlehome yuanlehome marked this pull request as ready for review October 13, 2025 08:07
@yuanlehome yuanlehome force-pushed the upgrade_limit_think_length branch from 62dd5da to 6f1f082 Compare October 14, 2025 10:24
K11OntheBoat
K11OntheBoat previously approved these changes Oct 16, 2025
Copy link
Collaborator

@K11OntheBoat K11OntheBoat left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这个注释删了

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

Copy link
Collaborator

@xiaoxiaohehe001 xiaoxiaohehe001 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@yuanlehome yuanlehome force-pushed the upgrade_limit_think_length branch from 96de19f to 849eaa6 Compare October 20, 2025 04:02
Copy link
Collaborator

@LiqinruiG LiqinruiG left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Collaborator

@gongshaotian gongshaotian left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@Jiang-Jia-Jun Jiang-Jia-Jun merged commit cef3164 into PaddlePaddle:develop Oct 20, 2025
13 of 16 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.

6 participants