Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
483 Open 6,790 Closed
483 Open 6,790 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

[https://nvbugs/5816267][fix] Remove weight tensor holder to release memory earlier
#10876 opened Jan 21, 2026 by dongxuy04 Loading…
1 task done
8
[https://nvbugs/5674665][fix] Fix accuracy drop in VSWA with KV cache block reuse
#10875 opened Jan 21, 2026 by SimengLiu-nv Loading…
1 task done
4
[None][fix] default disable gemm+allreduce fusion (#10656)
#10874 opened Jan 21, 2026 by benzh-2025 Loading…
1
[https://nvbugs/5769425][fix] add syncthreads for tinygemm to resolve intermittent accuracy problem
#10873 opened Jan 21, 2026 by dc3671 Loading…
1 task
3
[https://nvbugs/5741304][chore] Update flashinfer-python to 0.6.1
#10872 opened Jan 21, 2026 by yihwang-nv Loading…
6
[https://nvbugs/5741304][chore] Update flashinfer-python to 0.6.1
#10871 opened Jan 21, 2026 by yihwang-nv Loading…
7
[https://nvbugs/5740377][fix] Prevent out-of-bounds read
#10868 opened Jan 21, 2026 by HuiGao-NV Loading…
1 task done
7
[None][feat] AutoDeploy: Flashinfer kernels bringup
#10867 opened Jan 21, 2026 by nvchenghaoz Loading…
1 task
5
[https://nvbugs/5821433][fix] fix test_auto_scaling for 2 GPUs
#10866 opened Jan 21, 2026 by reasonsolo Loading…
1 task done
3
[None][fix] Fix PD disaggregation for VLMs that use mrope
#10865 opened Jan 21, 2026 by 2ez4bz Loading…
1 task done
10
[None][chore] Measure total time of AutoDeploy transforms
#10864 opened Jan 20, 2026 by taylor-yb-lee • Draft
1 task
[None][fix] Enable offline mode for HF models
#10863 opened Jan 20, 2026 by FrankD412 Loading…
1 task done
@FrankD412
12
[None][feat] Replace KV cache search structure with separate radix tree
#10862 opened Jan 20, 2026 by thorjohnsen • Draft
1 task
[TRTLLM-10319][feat] Dynamic draft length on spec decode one-model path
#10860 opened Jan 20, 2026 by zheyuf • Draft
1 task
[https://nvbugs/5791242][fix] add changes from PR 10713 (WAR for flashinfer.sampling.sampling_from_logits)
#10859 opened Jan 20, 2026 by v-shobhit • Draft
1 task
[https://nvbugs/5779536][fix] Unwaive Llama 3.3 related multi GPU tests
#10855 opened Jan 20, 2026 by pengbowang-nv • Draft
1 task
12
[https://nvbugs/5769815][fix] Fix offset calculation in _are_stop_words when using speculative decoding
#10854 opened Jan 20, 2026 by stnie • Draft
1 task
3
[https://nvbugs/5688721][fix] unwaive NemotronH accuracy test
#10852 opened Jan 20, 2026 by lucaslie Loading…
1 task done
@lucaslie
12
[https://nvbugs/5769712][fix] fix timeout in AutoDeploy llama accuracy test (#10461)
#10851 opened Jan 20, 2026 by lucaslie Loading…
1 task done
@lucaslie
12
[https://nvbugs/5814247][fix] AutoDeploy: skip mxfp4_moe test unless on Hopper (#10729)
#10850 opened Jan 20, 2026 by lucaslie Loading…
1 task done
@lucaslie
10
[None][chore] added AutoDeploy nano_v3_scale.yaml
#10845 opened Jan 20, 2026 by MrGeva Loading…
1 task done
6
[None][fix] Update RMSNorm custom op plumbing
#10843 opened Jan 20, 2026 by JintaoPengCS Loading…
1 task done
23
[https://nvbugs/5800646][fix] Fix hang issue by avoid exposing UB buf…
#10842 opened Jan 20, 2026 by liji-nv Loading…
1 task done
9
[https://nvbugs/5636916][fix] Cherry-pick #10654: Fix accuracy issue of TWO-SHOT AllReduce kernel
#10841 opened Jan 20, 2026 by hyukn Loading…
1 task done
10
[None][fix] Proper conditional compilation of sm10x cubins
#10839 opened Jan 20, 2026 by tongyuantongyu • Draft
1 task
2
ProTip! What’s not been updated in a month: updated:<2025-12-20.