Skip to content

Conversation

@luukunn
Copy link
Collaborator

@luukunn luukunn commented Sep 12, 2025

1.Modify the follow-up push parameter generated_token_ids to completion_token_ids.
2.Modify the verification method for reasoning_max_tokens so that when reasoning_max_tokens exceeds max_tokens, its value is set equal to max_tokens.

@paddle-bot
Copy link

paddle-bot bot commented Sep 12, 2025

Thanks for your contribution!

@paddle-bot paddle-bot bot added the contributor External developers label Sep 12, 2025
if metadata and metadata.get("generated_token_ids"):
self.append_generated_tokens(outputs, metadata["generated_token_ids"])
if metadata and metadata.get("completion_token_ids"):
self.append_completion_tokens(outputs, metadata["completion_token_ids"])
Copy link
Collaborator

Choose a reason for hiding this comment

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

本次修改去掉metadata, 直接从 request 中取。 需要再request 的 protocol 中增加该字段,同时修改 doc 文件。

Copy link
Collaborator

Choose a reason for hiding this comment

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

在 request 的 metadata 兼容的逻辑中, 如果metadata 不为空, 增加warnning 提示 此参数已经过时。

LiqinruiG
LiqinruiG previously approved these changes Sep 12, 2025
@Jiang-Jia-Jun Jiang-Jia-Jun merged commit ee9d8a8 into PaddlePaddle:develop Sep 19, 2025
23 of 28 checks passed
luukunn added a commit to luukunn/FastDeploy that referenced this pull request Sep 19, 2025
…hod for thinking length (PaddlePaddle#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test
Jiang-Jia-Jun pushed a commit that referenced this pull request Sep 22, 2025
…hod for thinking length (#4177)

* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix
Jiang-Jia-Jun pushed a commit that referenced this pull request Sep 25, 2025
* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

* [fix]update apply_chat_template (#4137)

* update apply_chat_template

* fix unittest

* fix unittest

* fix

* fix

* fix unit test

* fix

* fix unit test

* add unit test
Jiang-Jia-Jun pushed a commit that referenced this pull request Sep 28, 2025
…4294)

* [fix]Modify follow-up push parameters and Modify the verification method for thinking length (#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test

* fix

* [fix]update apply_chat_template (#4137)

* update apply_chat_template

* fix unittest

* fix unittest

* fix

* fix

* fix unit test

* fix

* fix unit test

* add unit test

* fix reasoning_max_tokens
luukunn added a commit to luukunn/FastDeploy that referenced this pull request Nov 4, 2025
…hod for thinking length (PaddlePaddle#4086)

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* 续推参数  generated_token_ids 修改成 completion_token_ids;修改思考长度校验方式

* add completion_token_ids

* add logger

* fix reasoning_max_tokens ParameterError

* add unittest

* add unittest

* add unittest

* add unittest

* add unittest

* add unit test
kxz2002 added a commit to kxz2002/FastDeploy that referenced this pull request Nov 5, 2025
Jiang-Jia-Jun pushed a commit that referenced this pull request Nov 5, 2025
…ation method for thinking length (#4086) (#4826)

* resolve #4086 conflict

* fix unit test
Deleter-D pushed a commit to Deleter-D/FastDeploy that referenced this pull request Nov 26, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

contributor External developers

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants