Skip to content

Conversation

@luukunn
Copy link
Owner

@luukunn luukunn commented Jul 29, 2025

No description provided.

Deleter-D and others added 30 commits July 22, 2025 19:36
* add sot warmup

* fix code style

* change batch_size list

* add param to config

* rm free_list settings && set sot_warmup_sizes

* finish debug with dynamic dims by type annotations

* add profile_run guard

* rm sth useless
* [CI] add codestyle_check action

* [CI] Integrate codestyle check via pre-commit in GitHub Actions
* Support FD block scheduler v1

* Support FD block scheduler v1

* Support FD block scheduler v1

* Fix according to copilot review

* Fix according to review

* Remove is_dummy

* Fix bug when real_bsz=1

* Fix infer first token cost time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
* add ci reuse action

* fix code formatting

* update
* multi-source download

* multi-source download

* huggingface download revision

* requirement

* style

* add revision arg

* test

* pre-commit
* update benchmark tools

* update benchmark tools
…le#3000)

* update flake8 version to support pre-commit in python3.12

* polish code
* multi-source download

* multi-source download

* huggingface download revision

* requirement

* style

* add revision arg

* test

* pre-commit

* Change default download

* change requirements.txt

* modify English Documentation

* documentation
littledgg and others added 5 commits July 24, 2025 20:15
* [Feature] support_eplb

* [Feature] support_eplb

* [Fix] fix mm ep
…ious raw_request (PaddlePaddle#3023)

* [feat] add disable_chat_template in chat api as a substitute for previous raw_request

* [fix] pre-commit code check
@luukunn luukunn merged commit c7194f7 into feature/tool-call Jul 29, 2025
@luukunn luukunn deleted the release/2.0.4 branch July 29, 2025 13:15
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.