Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
524 Open 7,326 Closed
524 Open 7,326 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][chore] split up TorchSampler.Store
#11566 opened Feb 18, 2026 by ixlmar • Draft
1 task done
4
Draft - DO NOT REVIEW - AD host time improvement for large prefill (and more changes that will be removed
#11565 opened Feb 18, 2026 by MrGeva Loading…
1 task
22
[None][chore] Add WAN2.1 FP8 VBench test
#11564 opened Feb 18, 2026 by yibinl-nvidia Loading…
1 task
@yibinl-nvidia
[None][feat] Add NVFP4 dynamic quantization support for visual_gen models
#11563 opened Feb 18, 2026 by chang-l Loading…
1 task done
10
[None][fix] Update to get central version variable for trtllm-bench.
#11562 opened Feb 18, 2026 by FrankD412 Loading…
1 task done
@FrankD412
4
fix sm120 int4
#11561 opened Feb 18, 2026 by pamelap-nvidia • Draft
1 task
5
[None][feat] Add GLM-4.7 FP8 recipe configs for H100 to config db
#11559 opened Feb 17, 2026 by venkywonka Loading…
1 task done
@venkywonka
4
[TRTLLM-10616][feat] Add FLUX.1 and FLUX.2 text-to-image pipeline support
#11556 opened Feb 17, 2026 by karljang • Draft
5 tasks done
14
Draft: DON'T REVIEW: improved perf of host time attention metadata list to tensor handling
#11555 opened Feb 17, 2026 by MrGeva Loading…
1 task
1
[None][feat] Visual Gen: add cuda graphs; torch compile; nvtx; warmup
#11554 opened Feb 17, 2026 by NVShreyas Loading…
1 task done
13
fix: prevent NIXL agent name collision in containerized disaggregated serving
#11552 opened Feb 17, 2026 by nv-yna • Draft
3 tasks
[None][infra] PLC pipeline update
#11547 opened Feb 17, 2026 by yuanjingx87 Loading…
1 task done
7
[None][infra] Cherry pick plc pipeline for 1.2
#11546 opened Feb 17, 2026 by yuanjingx87 Loading…
1 task done
13
[None][chore] Test change for CI workflow
#11545 opened Feb 17, 2026 by dpitman-nvda Loading…
1 task done
16
[None][fix] correct chunked prefill handling in TorchSampler
#11544 opened Feb 17, 2026 by ixlmar Loading…
1 task done
16
[https://nvbugs/839137][fix] Unwaive disagg unexpected ucx error
#11543 opened Feb 17, 2026 by pcastonguay Loading…
1 task done
4
Mf/minimax moe routing kernel Community want to contribute PRs initiated from Community
#11539 opened Feb 17, 2026 by michaelfeil • Draft
1 task
[None][ci] Reduce intermediate log size
#11537 opened Feb 16, 2026 by chzblych Loading…
1 task done
7
[None][chore] DO NOT MERGE: Waiving some tests for 1.3.0rc4
#11536 opened Feb 16, 2026 by pcastonguay Loading…
1 task done
9
[#10693][chore] AutoDeploy: Add L1 tests from coverage dashboard
#11530 opened Feb 15, 2026 by marinayanov Loading…
29
[#11312][chore] Make TRT/NCCL configurable in CMake find modules Community want to contribute PRs initiated from Community
#11528 opened Feb 15, 2026 by xuantengh Loading…
1 task done
10
[None][chore] Remove closed bugs
#11527 opened Feb 15, 2026 by xinhe-nv • Draft
[#11398][feat] AutoDeploy: flashinfer rope for GLM4.7-Flash AutoDeploy <NV> AutoDeploy Backend
#11524 opened Feb 14, 2026 by taylor-yb-lee Loading…
1 task done
1
14
Glm5 nvfp4 serving
#11522 opened Feb 14, 2026 by pst2154 Loading…
1 task done
8
[https://nvbugs/5875514][fix] Fix WideEP gen-only benchmark hang in disaggregated serving
#11521 opened Feb 14, 2026 by peihu-nv Loading…
1 task done
3
ProTip! no:milestone will show everything without a milestone.