-
Notifications
You must be signed in to change notification settings - Fork 2.6k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[https://nvbugs/6468821][chore] Unwaive GPT-OSS B300 attention backend test
#16616
opened Jul 20, 2026 by
yuxianq
Collaborator
Loading…
1 task done
[None][infra] Waive 1 failed cases for main in pre-merge 48660
#16615
opened Jul 20, 2026 by
trtllm-agent
Collaborator
Loading…
[None][Test] Consolidate dis-agg E2E Tests
#16614
opened Jul 20, 2026 by
Shixiaowei02
Collaborator
Loading…
1 task done
[None][fix] mpi_session: guard MpiPoolSession.shutdown against partial init
#16613
opened Jul 20, 2026 by
lowsfer
Member
Loading…
[TRTLLM-14474][chore] Remove legacy python relics and refresh docs after the backend removal
#16612
opened Jul 20, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[None][test] Add deepseek v4 pro cases on the qa side
#16611
opened Jul 20, 2026 by
fredricz-20070104
Collaborator
Loading…
[TRTLLM-14473][chore] Remove legacy TensorRT-backend tests, examples, and CI plumbing
#16610
opened Jul 20, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[TRTLLM-14027][infra] Remove --trt_root and stop installing the TensorRT SDK into images
#16608
opened Jul 20, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[https://nvbugs/6463987][perf] Revert NGC PyTorch 26.05 stack upgrade for GB300 GLM-5-fp4 ctx_only NVFP4 regression
#16601
opened Jul 20, 2026 by
chenfeiz0326
Collaborator
Loading…
3 tasks
[TRTLLM-11875][feat] MambaCacheManager based on KVCacheManagerV2 & agentic prefix caching
#16598
opened Jul 20, 2026 by
VALLIS-NERIA
Collaborator
•
Draft
1 task
[None][feat] Support MARLIN MoE with MTP and attention DP + EP
#16597
opened Jul 20, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[None][perf] Gate NCCL NVLS on NVML fabric state, not IMEX availability
#16595
opened Jul 20, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[TRTLLM-13233][feat] Support no_repeat_ngram_size in TorchSampler
#16594
opened Jul 20, 2026 by
zhaoyangwang-nvidia
Collaborator
•
Draft
1 task done
[TRTLLM-13409][fix] hard-kill all ranks when one rank's executor loop crashes
#16592
opened Jul 20, 2026 by
JunyiXu-nv
Collaborator
Loading…
1 task done
[https://nvbugs/6305365][chore] Unwaive piecewise cudagraph related tests
#16591
opened Jul 20, 2026 by
pengbowang-nv
Collaborator
Loading…
1 task done
[NVBUG-6448152][test] run additional async-consensus coverage
#16589
opened Jul 20, 2026 by
chienchunhung
Collaborator
•
Draft
[NVBUG-6448152][test] measure local-quiescence reclamation
#16581
opened Jul 19, 2026 by
chienchunhung
Collaborator
•
Draft
[NVBUG-6448152][test] isolate PP rendezvous from global commit
#16580
opened Jul 19, 2026 by
chienchunhung
Collaborator
•
Draft
[TRTLLMINF-218][infra] Gate multi-GPU CI stages behind 'ci: full pre-merge approved' label
#16578
opened Jul 19, 2026 by
ZhanruiSunCh
Collaborator
Loading…
1 task
[None][infra] Add dev-container entrypoint dispatcher for CLI docker workflow
#16574
opened Jul 19, 2026 by
jieli-matrix
Collaborator
•
Draft
2 of 8 tasks
[NVBUG-6448152][test] isolate CTX consensus regression
#16572
opened Jul 19, 2026 by
chienchunhung
Collaborator
•
Draft
[TRTLLM-14417][fix] Exclude ADP/cuda-graph dummy requests from speculative-decode acceptance stats
#16571
opened Jul 19, 2026 by
xwang233
Collaborator
Loading…
3 tasks done
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.