-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[None][feat] Feat/paperclip maximizer merge1
#12209
opened Mar 13, 2026 by
bmarimuthu-nv
•
Draft
1 task
[TRTLLM-11492][fix] Replace blocking fill loop with non-blocking can_forward gate in benchmark disagg mode
#12208
opened Mar 13, 2026 by
chienchunhung
•
Draft
1 task done
[None][infra] Waive failed A10-PyTorch-1 test in pre-merge
#12207
opened Mar 13, 2026 by
yuanjingx87
Loading…
1 task done
[None][feat] Add support for Gemma3n and sharedKV cache attention in AutoDeploy
#12205
opened Mar 13, 2026 by
bmarimuthu-nv
•
Draft
1 task done
[None][feat] Add support for Gemma3n and SharedKV cache attention layers in AutoDeploy
#12204
opened Mar 13, 2026 by
bmarimuthu-nv
•
Draft
1 task
[None][feat] Support Qwen3.5 Dense and MoE Models in Pytorch Backend
#12203
opened Mar 13, 2026 by
keddyjin
Loading…
[TRTLLM-11357][feat] Support interleaved thinking for trtllm-serve
#12199
opened Mar 13, 2026 by
JunyiXu-nv
Loading…
1 task done
[None][doc] Blog18 for NVLinkOneSided AlltoAll.
#12195
opened Mar 13, 2026 by
bobboli
Loading…
1 task
[TRTLLM-9019][feat] Expose video_pruning_rate as llmargs and fix nano-v2-vl
#12194
opened Mar 13, 2026 by
Wanli-Jiang
Loading…
1 task done
[None][fix] remove test_llm_api_autodeploy.py::TestNemotronSuperV3::t…
#12193
opened Mar 13, 2026 by
tcherckez-nvidia
Loading…
1 task done
[None][chore] Alltoall benchmark script refine (second time).
#12192
opened Mar 13, 2026 by
bobboli
Loading…
1 task
[TRTLLM-11267][feat] Add audio support for nemotron
#12191
opened Mar 13, 2026 by
2ez4bz
Loading…
1 task done
[None][fix] Fix W4A16 AWQ bias not applied on SM100 (Blackwell)
#12190
opened Mar 13, 2026 by
Tracin
Loading…
1 task done
[None][fix] replace busy-poll sleep in get_async_noblock with zmq async poller
Community want to contribute
PRs initiated from Community
#12189
opened Mar 13, 2026 by
edenfunf
Loading…
[None][fix] Fix KV cache V2 OOM with separate draft KV cache (EAGLE3/MTP)
#12188
opened Mar 13, 2026 by
yizhang-nv
Loading…
1 task done
[https://nvbugs/5973536][fix] Route DSA attention through MLA custom op for torch.compile compatibility
#12186
opened Mar 13, 2026 by
yizhang-nv
Loading…
1 task done
Draft: Linear attention support for KVCacheManager
#12185
opened Mar 13, 2026 by
VALLIS-NERIA
•
Draft
1 task
[None][fix] Add more models to increase perf test coverage
#12184
opened Mar 13, 2026 by
chenfeiz0326
Loading…
1 task done
[https://nvbugs/5879588][fix] fix MiniMax model loading bugs
#12182
opened Mar 13, 2026 by
jmydurant
Loading…
1 task
[None][fix] fix mooncake dynamic load in transfer_agent_binding
#12181
opened Mar 13, 2026 by
chuangz0
Loading…
1 task done
Previous Next
ProTip!
no:milestone will show everything without a milestone.