Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][feat] DSA: adaptive indexer prefill chunk size for long sequences
#15683
opened Jun 27, 2026 by
lfr-0531
Collaborator
Loading…
[https://nvbugs/6357628][fix] Pin params.seed=42 in wan_t2v.py; add per_dimension_tolerances to…
#15682
opened Jun 27, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[https://nvbugs/6379316][fix] Keep the prior
7e134dd249 gate that adds _is_pcie_nvl_sku() + DeepEP-LL…
#15681
opened Jun 27, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[#14575][feat] Add Qwen3.5/3.6 MoE NVFP4 + MTP support for SM120/SM121
#15680
opened Jun 27, 2026 by
mihai-chiorean
Contributor
Loading…
5 of 7 tasks
[None][test] Waive 1 failed cases for main in QA CI
#15678
opened Jun 26, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[TRTLLM-13546][feat] Add error classification patterns (1c.1)
#15677
opened Jun 26, 2026 by
chienchunhung
Collaborator
Loading…
[None][test] AutoDeploy: Fix standalone linear simple on B200
#15675
opened Jun 26, 2026 by
govind-ramnarayan
Collaborator
Loading…
1 task done
[TRTLLMINF-99][infra] Add SLURM frontend failover to L0
#15674
opened Jun 26, 2026 by
dpitman-nvda
Collaborator
Loading…
1 task done
[https://nvbugs/6369411][fix] Port commit 21ea62f24a: add _get_nccl_runtime_version_code() + lru-cached…
#15672
opened Jun 26, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][chore] split unittest/_torch/visual_gen
#15670
opened Jun 26, 2026 by
tburt-nv
Collaborator
Loading…
1 task done
[None][fix] Don't re-run the SLURM monitor on a terminal job failure
#15669
opened Jun 26, 2026 by
dpitman-nvda
Collaborator
Loading…
1 task done
[None][feat] feat: VisualGen TE-FP8 attention backend + per-layer quant
#15668
opened Jun 26, 2026 by
wu6u3tw
Contributor
Loading…
[None][test] Waive 2 failed cases for main in QA CI
#15667
opened Jun 26, 2026 by
tensorrt-cicd
Collaborator
•
Draft
[None][feat] Add Laguna DFlash drafter support
#15666
opened Jun 26, 2026 by
joerowell
Loading…
1 task done
[https://nvbugs/6372711][fix] Add module-level pytestmark = pytest.mark.threadleak(enabled=False) at the top…
#15664
opened Jun 26, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][test] record per-case hostname in perf result CSV
#15663
opened Jun 26, 2026 by
ruodil
Collaborator
Loading…
1 task done
[TRTLLM-13628][test] Optimize MoE comm test execution
#15662
opened Jun 26, 2026 by
sunnyqgg
Collaborator
Loading…
3 tasks done
[https://nvbugs/6316983][fix] Fix RoPE support in flashinfer trtllm-gen backend
#15661
opened Jun 26, 2026 by
yihwang-nv
Collaborator
Loading…
1 task
[None][fix] Fix marlin_nvfp4_template.h compilation error
#15660
opened Jun 26, 2026 by
yihwang-nv
Collaborator
Loading…
1 task
[None][fix] GLM-5.1 NVFP4 fallback to AR-Norm fusion for unquantized dense layers
#15659
opened Jun 26, 2026 by
syuoni
Collaborator
Loading…
1 task done
[https://nvbugs/6375002][fix] Pin params.seed=42 in wan_t2v.py; add per_dimension_tolerances kwarg to…
#15657
opened Jun 26, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][feat] Optimize trtllmgen moe routing
#15656
opened Jun 26, 2026 by
jiahanc
Collaborator
Loading…
1 task done
[https://nvbugs/6344107][fix] Enable disagg partial reuse store for PP>1
#15655
opened Jun 26, 2026 by
nv-xtf
Collaborator
Loading…
1 task done
ProTip!
Updated in the last three days: updated:>2026-06-24.