Yuanle Liu
|
2b79d971f1
|
[Cherry-Pick][OP][Feature] 统一 limit_thinking_content_length CUDA 算子,支持回复长度限制与注入序列 (#6506)
* Initial plan
* feat: migrate core PR6493 changes to release 2.4
Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>
* fix ci
* fix ci
* fix ci
* fix ci
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>
|
2026-02-25 18:02:01 -08:00 |
|