Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
787 Open 10,513 Closed
787 Open 10,513 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 tinygemm barrier bug
#15338 opened Jun 13, 2026 by yweng0828 Collaborator Loading…
1 task done
@yweng0828
3
[None][test] Waive 23 failed cases for main in QA CI
#15337 opened Jun 13, 2026 by tensorrt-cicd Collaborator • Draft
@tensorrt-cicd
[None][test] CI-only: probe gb200 deepseek-v32 perf-sanity at 5f106dfa (DO NOT MERGE)
#15336 opened Jun 13, 2026 by tensorrt-cicd Collaborator • Draft
@tensorrt-cicd
4
[TRTLLM-12807][test] Guard thop attention kwarg aliases
#15335 opened Jun 13, 2026 by yuxianq Collaborator Loading…
1 task done
@yuxianq
4
[None][test] Waive 5 failed cases for main in QA CI
#15334 opened Jun 13, 2026 by tensorrt-cicd Collaborator • Draft
@tensorrt-cicd
[TRTLLM-12807][feat] Wrap CuteDSL MLA decode as FMHA lib
#15333 opened Jun 13, 2026 by yuxianq Collaborator • Draft
1 task done
@yuxianq
[https://nvbugs/6281014][fix] fix the repeated cute.compile and simpilify the test
#15331 opened Jun 13, 2026 by JadoTu Collaborator Loading…
1 task done
@JadoTu
4
[None][chore] Simplify MoE lora
#15330 opened Jun 12, 2026 by brb-nv Collaborator • Draft
1 task
@brb-nv
[#15327][feat] Add per-request priority support to OpenAI chat/completions
#15329 opened Jun 12, 2026 by sopwg612 Loading…
1 task done
1
@sopwg612
1
[https://nvbugs/6306936][test] Re-enable AutoDeploy disagg tests
#15325 opened Jun 12, 2026 by govind-ramnarayan Collaborator Loading…
1 task done
@govind-ramnarayan
5
[TRTLLM-12721][perf] Remove ready-ID transfer gathers
#15324 opened Jun 12, 2026 by chienchunhung Collaborator • Draft
@chienchunhung
3
[None][test] Fix Mamba hybrid transceiver helper
#15323 opened Jun 12, 2026 by chienchunhung Collaborator Loading…
@chienchunhung
4
[None][chore] Small cleanups to MultimodalModelMixin
#15322 opened Jun 12, 2026 by 2ez4bz Collaborator Loading…
1 task done
@2ez4bz
11
[https://nvbugs/6193854][fix] PR #14851 already removed the bad is_sliding_window/mMaxSeqLenKv logic on…
#15321 opened Jun 12, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@tensorrt-cicd
1
[None][test] Waive 1 failed cases for main in QA CI
#15320 opened Jun 12, 2026 by tensorrt-cicd Collaborator • Draft
@tensorrt-cicd
[None][test] Waive 3 failed cases for main in QA CI
#15319 opened Jun 12, 2026 by tensorrt-cicd Collaborator Loading…
@jieli-matrix @tensorrt-cicd
7
[None][fix] visual_gen/wan: emulate eager precision casts under torch.compile
#15318 opened Jun 12, 2026 by karljang Collaborator Loading…
@karljang
4
[None][test] Waive 1 failed cases for main in QA CI
#15315 opened Jun 12, 2026 by tensorrt-cicd Collaborator Loading…
@jieli-matrix @tensorrt-cicd
4
feat(visual_gen): NIXL P2P transport for ring-attention KV exchange
#15314 opened Jun 12, 2026 by pkisfaludi-nv Loading…
5 tasks
@pkisfaludi-nv
5
[None][feat] Add PyTorch reset_prefix_cache API api-compatible Accepted LLM API contract change that is backwards-compatible
#15313 opened Jun 12, 2026 by milesial Collaborator • Draft
1 task done
@milesial
6
[https://nvbugs/6270671][fix] Replace the hardcoded multiBlock=1 with a call to…
#15312 opened Jun 12, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@mikeiovine @tensorrt-cicd
2
[None][perf] Bound Triton MoE JIT specializations via token-dim bucketing and warmup
#15311 opened Jun 12, 2026 by arysef Collaborator • Draft
4 tasks done
@arysef
[None][fix] disagg: use ctx retry id for gen request
#15309 opened Jun 12, 2026 by liji-nv Collaborator Loading…
1 task done
@liji-nv
3
[None][feat] Kv transfer p2p path
#15308 opened Jun 12, 2026 by chuangz0 Collaborator Loading…
1 task done
@chuangz0
11
[None][fix] Fix V2 context finalization ordering
#15307 opened Jun 12, 2026 by jiaganc Collaborator • Draft
1 task done
@jiaganc
ProTip! Add no:assignee to see everything that’s not assigned.