qwen 3.8 rebase (#35758)

Co-authored-by: cherichy <cherichy@outlook.com>
Co-authored-by: guangyunh-nv <guangyunh@nvidia.com>
Co-authored-by: jiahanc <jiahanc@nvidia.com>
Co-authored-by: jinyangyuan-nvidia <joyuan@nvidia.com>
Co-authored-by: Cheng Hang <chang@nvidia.com>
Co-authored-by: Yicheng Qiang <yqiang@nvidia.com>
Co-authored-by: Sam Li <lsam@nvidia.com>
Co-authored-by: Tom-Zheng <tizheng@nvidia.com>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: xiaoweiw-nv <xiaoweiw@nvidia.com>
Co-authored-by: Zheng Li <lizheng.cs@zju.edu.cn>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This commit is contained in:
Qiaolin Yu
2026-08-28 20:41:34 -07:00
committed by GitHub
co-authored by cherichy guangyunh-nv jiahanc jinyangyuan-nvidia Cheng Hang Yicheng Qiang Sam Li Tom-Zheng Yangmin Li xiaoweiw-nv Zheng Li yizhang2077 Ke Bao Xinyuan Tong Yuhao Yang Zijie Xia github-actions[bot]
parent ca8cc101b8
commit 5f216fc33f
97 changed files with 14483 additions and 373 deletions
+3
View File
@@ -497,6 +497,9 @@ class MoeFlags(_FlagGroupBase):
# speculative_moe_backend_context is active, so a draft gate's write also
# lands on the speculative leaf.
in_speculative_scope: bool = False
# Draft construction/execution uses a separate one-sided A2A workspace from
# the target model's concurrently live CUDA graphs.
speculative_context: bool = False
@dataclasses.dataclass