Skip to content

Pull requests: NVIDIA/TensorRT-LLM

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[None][feat] Add opt-in GPU keepalive for idle executor windows
#18749 opened Sep 5, 2026 by qiaoxj07 Collaborator Draft
1 task done
[https://nvbugs/6721558][fix] Route all three streaming sites through a new…
#18746 opened Sep 5, 2026 by trtllm-agent Collaborator Loading…
2 tasks done
[None][fix] Size seq-slot pool to cover disagg-gen KV admission
#18742 opened Sep 5, 2026 by brb-nv Collaborator Loading…
1 task done
[None][test] Add InferenceMAX-style GSM8K accuracy eval mode
#18738 opened Sep 4, 2026 by zheyuf Collaborator Draft
3 of 4 tasks
[None][fix] Re-resolve the TRTLLM-Gen MoE op provider after layer quant
#18735 opened Sep 4, 2026 by moraxu Collaborator Draft
1 task done
[None][fix] Keep split gate/up NVFP4 global scales on TRTLLM-Gen MoE
#18734 opened Sep 4, 2026 by moraxu Collaborator Draft
1 task done
[None][feat] Add MiniMax H3 support VisualGen
#18733 opened Sep 4, 2026 by yibinl-nvidia Collaborator Draft
1 task done
[TRTLLMINF-396][ci] Auto-label fully approved pre-merge PRs
#18729 opened Sep 4, 2026 by ZhanruiSunCh Collaborator Loading…
1 task
[None][fix] share Kimi auxiliary streams
#18728 opened Sep 4, 2026 by jiaganc Collaborator Loading…
1 task done
[None][fix] Preserve configured Mamba snapshot placement
#18724 opened Sep 4, 2026 by liji-nv Collaborator Loading…
1 task
ProTip! no:milestone will show everything without a milestone.