Skip to content

[None][feat] GEN slot preemption: pause decode requests in place to admit at-risk waiters - #21334

Open
reasonsolo wants to merge 13 commits into
NVIDIA:mainfrom
reasonsolo:user/lizhiz/gen-preemption-pr
Open

[None][feat] GEN slot preemption: pause decode requests in place to admit at-risk waiters#21334
reasonsolo wants to merge 13 commits into
NVIDIA:mainfrom
reasonsolo:user/lizhiz/gen-preemption-pr

Merge NVIDIA/TensorRT-LLM main into user/lizhiz/gen-preemption-pr

b3c3d64
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Nov 4, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO