Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
473 Open 6,734 Closed
473 Open 6,734 Closed
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
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[None][doc] Update Qwen2/3-VL's model on supported_models.md Multimodal Label for issues & PRs regarding Multimodal related objects
#10797 opened Jan 19, 2026 by yechank-nvidia Loading…
@yechank-nvidia
4
[None][feat] K-EXAONE MTP support
#10796 opened Jan 19, 2026 by yechank-nvidia Loading…
@yechank-nvidia
8
[https://nvbugs/5814253][fix] unwaive test_autotuner_distributed_strategy tests
#10793 opened Jan 19, 2026 by hyukn Loading…
1 task done
4
[None][chore] switch to ConfigurableMoE as the default path
#10792 opened Jan 19, 2026 by xxi-nv Loading…
1 task done
9
[TRTLLM-10398][feat] Enable TRTLLM moe backend for Nemotron Super
#10791 opened Jan 19, 2026 by nv-guomingz • Draft
1 task
[https://nvbugs/5814247][fix] unwaive AutoDeploy multi-gpu unit tests
#10789 opened Jan 19, 2026 by hyukn Loading…
1 task done
6
Draft: Support context sparse attention for mqa/gqa
#10788 opened Jan 19, 2026 by heyuhhh Loading…
1 task
15
[None][chore] Add failed cases into waives.txt
#10787 opened Jan 18, 2026 by xinhe-nv • Draft
[TRTLLM-10785][feat] Fix sharding dashboard errors
#10786 opened Jan 18, 2026 by greg-kwasniewski1 Loading…
1 task done
1
9
[None][feat] Initial patch for trtllm-gen attention backend
#10784 opened Jan 18, 2026 by yihwang-nv Loading…
10
[TRTLLM-9581][Infra] Use /home/scratch.trt_llm_data_ci in computelab
#10783 opened Jan 18, 2026 by ZhanruiSunCh Loading…
1 task
7
Draft: AutoDeploy fx graph export cache
#10782 opened Jan 18, 2026 by MrGeva Loading…
1 task
7
[None][fix] AutoDeploy: Support per-expert input scales for FP8 MoE
#10778 opened Jan 18, 2026 by galagam Loading…
1 task done
@galagam
9
[None][chore] Add failed cases into waives.txt
#10776 opened Jan 18, 2026 by xinhe-nv • Draft
@jieli-matrix
[TRTLLM-10774][feat] fix sharding tests
#10775 opened Jan 17, 2026 by greg-kwasniewski1 Loading…
1 task done
1
15
[DRAFT][AutoDeploy] Enhance memory consumption for moe fusion transform
#10772 opened Jan 17, 2026 by taylor-yb-lee • Draft
1 task
[TRTLLM-10325][feat] Refactor speculative decoding workers
#10768 opened Jan 16, 2026 by cascade812 Loading…
1 task done
12
[#9525][feat] add L2 norm pattern matcher and fusion transform
#10767 opened Jan 16, 2026 by karthikvetrivel Loading…
1 task done
14
[https://nvbugs/5814914][fix] Fix llama sm120 spec dec
#10765 opened Jan 16, 2026 by mikeiovine Loading…
1 task done
4
[https://nvbugs/5748664][fix] Increasing disagg acc test timeout
#10764 opened Jan 16, 2026 by pcastonguay Loading…
1 task done
8
[None][test] Update test case for release
#10763 opened Jan 16, 2026 by crazydemo Loading…
1 task done
7
[None][fix] Fix waived tests for Nemotron-h models
#10758 opened Jan 16, 2026 by Wanli-Jiang • Draft
1 task done
6
[TRTLLM-10453][feat] Update mamba decode kernel to flashinfer
#10757 opened Jan 16, 2026 by Wanli-Jiang • Draft
1 task
[https://nvbugs/5814203][fix] Fix port 8000 being used issue in stress test.
#10756 opened Jan 16, 2026 by dominicshanshan Loading…
1 task done
9
[None] [fix] Remove unnecessary ValueError
#10755 opened Jan 16, 2026 by kaiyux Loading…
1 task done
9
ProTip! Updated in the last three days: updated:>2026-01-15.