Skip to content

Host the Qwen3.8-Flash CUDA-graph decode loop in the Engine's static path - #2728

Open
Tianlei Wu (tianleiwu) wants to merge 17 commits into
tlwu/20261013/ga-b3-qwen38-graph-modelfrom
tlwu/20261013/ga-b4-qwen38-engine-host
Open

Host the Qwen3.8-Flash CUDA-graph decode loop in the Engine's static path#2728
Tianlei Wu (tianleiwu) wants to merge 17 commits into
tlwu/20261013/ga-b3-qwen38-graph-modelfrom
tlwu/20261013/ga-b4-qwen38-engine-host

fix(engine): address review feedback on re-enrollment, deferred devic…

1786dd4
Select commit
Loading
Failed to load commit list.
Azure Pipelines / macOS arm64 Build completed Nov 1, 2026 in 0s

This check was skipped

No pipeline branch filters matched the modified branch.

View more details on Azure Pipelines