Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
432 Open 5,141 Closed
432 Open 5,141 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][test] add deepseek and qwen cases for rtx series
#8839 opened Oct 31, 2025 by ruodil Loading…
1 task done
@ruodil
4
[TRTLLM-8994][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0
#8838 opened Oct 31, 2025 by ZhanruiSunCh Loading…
1 task done
5
[https://nvbugs/5521799][fix] add harmony channel validation
#8837 opened Oct 31, 2025 by xinhe-nv Loading…
1 task done
4
[None][feat] Fix attention sink load in xqa
#8836 opened Oct 31, 2025 by qsang-nv Loading…
1 task done
3
[None][chore] Update test list
#8835 opened Oct 31, 2025 by crazydemo Loading…
1 task done
3
[https://nvbugs/5606268][fix] Fix program exit segment fault triggered CublasMMWarpper deconstructor
#8834 opened Oct 31, 2025 by yunruis Loading…
1 task done
8
[https://nvbugs/5461796][fix] Unwaive test
#8832 opened Oct 31, 2025 by sunnyqgg Loading…
1 task done
3
[https://nvbugs/5608930][fix] Unwaive test 5608930
#8831 opened Oct 31, 2025 by sunnyqgg Loading…
1 task done
1
Maybe fix for improper reuse
#8830 opened Oct 31, 2025 by thorjohnsen Loading…
1 task
3
[https://nvbugs/5625990][chore] Add test coverage for current incapability of the KV cache manager
#8829 opened Oct 31, 2025 by eopXD Loading…
1 task done
7
[None][fix] Fix import issues in layer-wise benchmarks
#8827 opened Oct 31, 2025 by yuantailing Loading…
1 task done
13
[None][chore] Add sample yaml for wide-ep example and minor fixes
#8825 opened Oct 31, 2025 by kaiyux • Draft
1 task done
2
[None][perf] AutoDeploy optimize _get_unique_value
#8822 opened Oct 31, 2025 by suyoggupta Loading…
1 task
7
[TRTLLM-8814][feat] AutoDeploy: Use TRTLLM kernels for FP8 linear
#8820 opened Oct 31, 2025 by nvchenghaoz Loading…
1
4
[None] Change NIXL build type to release Community want to contribute PRs initiated from Community
#8818 opened Oct 30, 2025 by tanmayv25 Loading…
1 task
1
[None][fixes] Add tool call parsing fixes and Qwen3 coder parser
#8817 opened Oct 30, 2025 by 2ez4bz • Draft
2 tasks
2
[TRTLLM-8772][chore] Fuse indexer q proj into MLA Q up_proj
#8816 opened Oct 30, 2025 by chang-l • Draft
1 task done
[None][chore] Add error message for multiple response sampler_param with PyTorch backend
#8815 opened Oct 30, 2025 by yibinl-nvidia Loading…
1 task
3
[#8763][fix] AutoDeploy: correct mamba cache dtype extraction
#8812 opened Oct 30, 2025 by lucaslie Loading…
1 task done
1
@lucaslie
1
[None][feat] Make 2-model spec dec use the 1-model kernels (Hopper)
#8810 opened Oct 30, 2025 by mikeiovine Loading…
1 task done
6
[https://nvbugs/5474119][fix] Re-enable test
#8809 opened Oct 30, 2025 by dongfengy Loading…
1 task done
6
[#8476][chore] Update license
#8807 opened Oct 30, 2025 by karljang Loading…
1 task done
3
[https://nvbugs/5587574][fix] Increase server timeout to wait for weight loading
#8806 opened Oct 30, 2025 by pcastonguay Loading…
1 task done
4
[https://nvbugs/5527655][feat] Add NUMA-aware CPU affinity autoconfig
#8805 opened Oct 30, 2025 by dhansen-nvidia Loading…
1 task done
9
[#8781][fix] Cache the AllReduce wrapper to avoid re-allocating workspace which caused a hang
#8803 opened Oct 30, 2025 by MrGeva Loading…
1 task done
5
ProTip! Type g i on any issue or pull request to go back to the issue listing page.