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 Qwen3.8-Flash-Next support api-compatible Accepted LLM API contract change that is backwards-compatible
#18585 opened Sep 2, 2026 by Wanli-Jiang Collaborator Loading…
1 task done
[None][feat] Track KV cache reuse hit tokens by source tier
#18583 opened Sep 2, 2026 by yizhang-nv Member Loading…
7 tasks done
[None][docs] use positional model path for trtllm-serve examples
#18582 opened Sep 2, 2026 by imitater-dou Loading…
3 tasks done
[None][test] prune Gemma 3 checkpoint tests VisualGen
#18580 opened Sep 2, 2026 by xinhe-nv Collaborator Loading…
1 task done
[None][feat] Add XingChen4 model support
#18578 opened Sep 2, 2026 by wanghui002 Draft
5 of 6 tasks
[None][fix] Let the kernel ledger record comm kernels and partial ncu captures
#18574 opened Sep 2, 2026 by kaiyux Member Loading…
1 task done
[None][infra] Avoid false CBTS follow-up for test lists
#18573 opened Sep 2, 2026 by crazydemo Collaborator Loading…
[None][test] Add ModelExpress post-merge accuracy canaries
#18561 opened Sep 2, 2026 by moraxu Collaborator Draft
3 of 5 tasks
[TRTLLM-14881][feat] qualify Mistral dense for MX
#18558 opened Sep 1, 2026 by moraxu Collaborator Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.