-
Notifications
You must be signed in to change notification settings - Fork 2.3k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[None][fix] Always sync local ranks after prefetch in HfWeightLoader
#13556
opened Apr 28, 2026 by
lancelly
Collaborator
Loading…
[https://nvbugs/6087632][fix] fix test def to use local model
#13555
opened Apr 28, 2026 by
bo-nv
Collaborator
Loading…
1 task
[None][Refactor] Minor refactor SSM page table for extensibility
#13554
opened Apr 28, 2026 by
Shixiaowei02
Collaborator
•
Draft
1 task
[None][test] Test coverage and repro for #13320
#13553
opened Apr 28, 2026 by
eopXD
Collaborator
Loading…
1 task done
[https://nvbugs/6114821][fix] Remove torch.compile from spec dec sampling to prevent NCCL deadlock
#13552
opened Apr 28, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][test] Unwaive DSR1 V32 Agg TEP tests
#13550
opened Apr 28, 2026 by
chenfeiz0326
Collaborator
Loading…
1 task done
[None][feat] Improve memory calculation for mamba hybrid models when block reuse is off
#13549
opened Apr 28, 2026 by
VALLIS-NERIA
Collaborator
Loading…
1 task done
[None][doc] Blogpost for Helix Parallelism
#13547
opened Apr 28, 2026 by
brb-nv
Collaborator
Loading…
1 task done
disagg support of cpp/KVCacheManager+LinearAttention
#13546
opened Apr 28, 2026 by
VALLIS-NERIA
Collaborator
•
Draft
1 task
[TRTLLM-11228][feat] Update quickstart for DFlash
#13545
opened Apr 28, 2026 by
ziyixiong-nv
Collaborator
Loading…
1 task
[https://nvbugs/6029882][fix] Clamp tokens_info writes in computeSeqAndPaddingOffsets
#13544
opened Apr 28, 2026 by
bobboli
Collaborator
Loading…
2 of 3 tasks
Fix beam-search requests not terminating at large beam_width
Community want to contribute
PRs initiated from Community
#13543
opened Apr 28, 2026 by
Doloxetine
Loading…
[None][chore] Convert cubins in repository to compressed archives
#13542
opened Apr 28, 2026 by
tongyuantongyu
Member
Loading…
1 task done
[https://nvbugs/6098442][fix] Add fix for IMA with TRTLLM-Gen GmemReductionWithSeparateKernel
#13541
opened Apr 28, 2026 by
pengbowang-nv
Collaborator
Loading…
1 task done
[None][test] Waive 9 failed cases for main in QA CI
#13540
opened Apr 28, 2026 by
xinhe-nv
Collaborator
Loading…
[None][test] rename test case and add fallback for multinode cases
#13537
opened Apr 28, 2026 by
ruodil
Collaborator
Loading…
1 task done
[None][fix] write per-rank torch profile traces
#13536
opened Apr 28, 2026 by
GavinZhu-GMI
Loading…
3 of 4 tasks
[https://nvbugs/6112510][fix] Reserve activation memory in KV cache budget and fix stress test artifacts direc
#13533
opened Apr 28, 2026 by
tensorrt-cicd
Collaborator
Loading…
2 tasks done
[None][chore] AutoDeploy: Remove Two Model Speculative Decoding Support
#13532
opened Apr 28, 2026 by
govind-ramnarayan
Collaborator
Loading…
1 task done
[TRTLLM-11851][feat] Add MX-only P2P checkpoint loading support for TRTLLM
#13531
opened Apr 27, 2026 by
chienchunhung
Collaborator
•
Draft
1 task done
[TRTLLMINF-43][feat] Extend infrastructure-failure retry to K8s test stages
#13530
opened Apr 27, 2026 by
dpitman-nvda
Collaborator
Loading…
1 task done
[None][fix] fix PEFT page accumulation in MaxUtilizationPolicy scheduler
#13528
opened Apr 27, 2026 by
achartier
Collaborator
Loading…
1 task done
[https://nvbugs/5996024][fix] Enforce trust_remote_code flag
#13527
opened Apr 27, 2026 by
yibinl-nvidia
Collaborator
•
Draft
1 task
[TRTLLMINF-45][infra] Upload rendered HTML failure analysis
#13526
opened Apr 27, 2026 by
dpitman-nvda
Collaborator
Loading…
1 task done
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.