Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
401 Open 4,796 Closed
401 Open 4,796 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] Add failed cases into waives.txt
#8400 opened Oct 15, 2025 by xinhe-nv • Draft
[https://nvbugs/5502901][fix] Set max_seq_len and max_batch_size in TestNemotronUltra test cases to prevent OOM
#8399 opened Oct 15, 2025 by amitz-nv Loading…
1 task
@amitz-nv
3
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements
#8398 opened Oct 15, 2025 by ixlmar • Draft
1 task done
2
[https://nvbugs/5437384][test] fix trtllm-llmapi-launch multi tests with single launch
#8397 opened Oct 15, 2025 by Superjomn Loading…
1 task done
13
[None][chore] Cleanup KV cache manager
#8396 opened Oct 15, 2025 by Funatiq • Draft
1 task
3
[none][feat] Support nano-v2-vlm with multiple PRs
#8395 opened Oct 15, 2025 by Wanli-Jiang • Draft
[TRTLLM-8669][infra] Use artifactory mirror for install python
#8394 opened Oct 15, 2025 by ZhanruiSunCh Loading…
1 task
6
[None][feat] Add fmha_v2 kernel for head_dim=80 and sm=100 to support VLM
#8392 opened Oct 15, 2025 by Wanli-Jiang Loading…
1 task done
6
[https://nvbugs/5540138][fix] Fix shape error when duplicating kv.
#8390 opened Oct 15, 2025 by Tracin Loading…
1 task
9
[None][test] cherry-pick: add test-model-suites in integration conftest.py
#8388 opened Oct 15, 2025 by ruodil Loading…
1 task done
7
[None][fix] improve mpirun hang issues
#8385 opened Oct 15, 2025 by xinhe-nv • Draft
1 task
Ampere xqa swa specdec
#8383 opened Oct 15, 2025 by jhaotingc Loading…
1 task
4
[TRTLLM-8464][infra] Use public triton 3.5.0
#8382 opened Oct 15, 2025 by ZhanruiSunCh Loading…
1 task
11
[None][fix] fix error when processing batches containing both text and mm data Community want to contribute PRs initiated from Community
#8381 opened Oct 15, 2025 by Nekofish-L Loading…
1 task done
3
[None][fix] fix visual encoder attention weight loading for Qwen2.5-VL tp deployment (sm < 100) Community want to contribute PRs initiated from Community
#8380 opened Oct 15, 2025 by Nekofish-L Loading…
1 task done
3
[https://nvbugs/5542862][fix] Upgrade fmha_v2 cubins compiled with cuda 13.0
#8379 opened Oct 15, 2025 by PerkzZheng Loading…
1 task done
1
[None][chore] update test duration
#8377 opened Oct 15, 2025 by xinhe-nv Loading…
1 task done
1
Draft: [http://nvbugs/5552889][fix] fix: Prevent empty batch when using attention DP with disagg
#8372 opened Oct 14, 2025 by pcastonguay Loading…
1 task
9
[None][feat] Update devcontainer configuration to include additional extensions
#8369 opened Oct 14, 2025 by Funatiq Loading…
1 task done
6
[None][fix] Fix request_id for best_of/n case
#8368 opened Oct 14, 2025 by evezhier Loading…
1 task done
1
[TRTLLM-6741] [feat] Extend lm_head_tp_size to world_size
#8367 opened Oct 14, 2025 by kaiyux Loading…
1 task
16
[None][feat] Add max_total_draft_tokens
#8366 opened Oct 14, 2025 by yweng0828 Loading…
1 task done
41
[https://nvbugs/5542862][fix] Upgrade fmha_v2.
#8364 opened Oct 14, 2025 by yuxianq Loading…
1 task done
6
[https://nvbugs/5461761][fix] Unwaive eagle3 test
#8363 opened Oct 14, 2025 by sunnygqq Loading…
1 task done
6
[None][feat] Dev DeepConf
#8362 opened Oct 14, 2025 by dcaox Loading…
1 task done
32
ProTip! Follow long discussions with comments:>50.