Skip to content

Pull requests: NVIDIA/TensorRT-LLM

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[https://nvbugs/6451032][fix] Reserve extra dflash KV slot for dummy requests
#16548 opened Jul 17, 2026 by amukkara Collaborator Loading…
1 task done
[None][chore] update allowlist 2026-07-17
#16547 opened Jul 17, 2026 by tburt-nv Collaborator Loading…
1 task done
[https://nvbugs/6438658][fix] Fix KV cache estimation capacity
#16545 opened Jul 17, 2026 by jiaganc Collaborator Draft
1 task done
[None][feat] Support rejection sampling under attention DP (incl. LM-head TP) api-compatible Accepted LLM API contract change that is backwards-compatible
#16544 opened Jul 17, 2026 by zhaoyangwang-nvidia Collaborator Loading…
1 task done
[None][test] remove MiniMax-M2 tp16 multinode eval test case
#16542 opened Jul 17, 2026 by jieli-matrix Collaborator Loading…
1 task done
[None][test] Add DeepSeek-V4-Pro perf sanity cases on GB300
#16540 opened Jul 17, 2026 by chenfeiz0326 Collaborator Loading…
6 tasks done
[https://nvbugs/6395830][fix] Qwen-VL mRoPE: move seq-slot delta cach…
#16537 opened Jul 17, 2026 by nv-guomingz Collaborator Loading…
1 task
[https://nvbugs/6316983][chore] Unwaive TestQwen2_5_VL_7B::test_auto_dtype
#16534 opened Jul 17, 2026 by yihwang-nv Collaborator Loading…
1 task
[None][perf] Fuse DeepSeek-V4 Indexer Q projection with CuTe DSL
#16532 opened Jul 17, 2026 by mingyangHao Collaborator Loading…
1 task done
[None][chore] Update flashinfer-python from 0.6.14 to 0.6.15
#16530 opened Jul 17, 2026 by yihwang-nv Collaborator Loading…
4 tasks
[None][feat] Default GLM-5 to the Python KV-cache transceiver
#16524 opened Jul 17, 2026 by chuangz0 Collaborator Loading…
1 task done
[None][feat] serve: multi-process HTTP frontends on the classic IPC executor path api-compatible Accepted LLM API contract change that is backwards-compatible
#16523 opened Jul 17, 2026 by lancelly Collaborator Loading…
[https://nvbugs/6163690][fix] Upgrade transformers to 5.10.1
#16516 opened Jul 17, 2026 by pamelap-nvidia Collaborator Loading…
1 task done
ProTip! Adding no:label will show everything without a label.