Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
398 Open 4,784 Closed
398 Open 4,784 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][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
[None] [chore] Add OSS compliance to CODEOWNERS
#8375 opened Oct 14, 2025 by venkywonka Loading…
1 task done
@venkywonka
3
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
7
[None][feat] Update devcontainer configuration to include additional extensions
#8369 opened Oct 14, 2025 by Funatiq Loading…
1 task
2
[None][fix] Fix request_id for best_of/n case
#8368 opened Oct 14, 2025 by evezhier Loading…
1 task
1
[TRTLLM-6741] [feat] Extend lm_head_tp_size to 8
#8367 opened Oct 14, 2025 by kaiyux Loading…
1 task
13
[None][feat] Add max_total_draft_tokens
#8366 opened Oct 14, 2025 by yweng0828 Loading…
1 task done
35
[https://nvbugs/5542862][fix] Upgrade fmha_v2.
#8364 opened Oct 14, 2025 by yuxianq Loading…
1 task done
6
[https://nvbugs/5461761][fix] Unwaive test fix bug 5461761
#8363 opened Oct 14, 2025 by sunnygqq Loading…
1 task
5
[None][feat] Dev DeepConf
#8362 opened Oct 14, 2025 by dcaox Loading…
1 task done
18
[TRTLLM-8464][infra] Use public triton 3.5.0
#8361 opened Oct 14, 2025 by ZhanruiSunCh Loading…
1 task
9
[TRTLLM-4866] [test] Support waiving unit tests by waives.txt
#8359 opened Oct 14, 2025 by VALLIS-NERIA Loading…
1 task
10
[None][test] remove redunctant runtime backend in perf test
#8358 opened Oct 14, 2025 by ruodil • Draft
1 task done
3
[TRTLLM-8113][test] Add pytorch workflow e2e tests with pp enabled
#8357 opened Oct 14, 2025 by StanleySun639 Loading…
1 task done
7
[None][chore] Update nim test list
#8356 opened Oct 14, 2025 by crazydemo Loading…
1 task done
11
[https://nvbugs/5541494] [fix] Remove waivers
#8353 opened Oct 14, 2025 by VALLIS-NERIA Loading…
1 task done
10
[None][doc] Add LLM-API API change principle
#8350 opened Oct 14, 2025 by Superjomn Loading…
1 task
4
[TRTLLM-7008][fix] unwaive online eplb multi-GPU tests
#8348 opened Oct 14, 2025 by dongxuy04 • Draft
1 task done
10
[None][fix] Move transfer remaining logits logic to handle_response
#8345 opened Oct 14, 2025 by yibinl-nvidia • Draft
1 task
3
[https://nvbugs/5534705][fix] Skip unnecessary CUDA graph capture (#8…
#8344 opened Oct 14, 2025 by ziyixiong-nv Loading…
1 task
9
[None][feat] Add FP8 rowwise GEMMs for B200
#8332 opened Oct 13, 2025 by achartier • Draft
1 task done
2
[None][chore] Standardize LlmArgs initialization and parsing around Pydantic
#8331 opened Oct 13, 2025 by anish-shanbhag • Draft
1 task
ProTip! What’s not been updated in a month: updated:<2025-09-14.