Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
793 Open 9,451 Closed
793 Open 9,451 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] gitignore NFS system temporary files
#14211 opened May 17, 2026 by zhenhuaw-me Member Loading…
1 task done
@zhenhuaw-me
1
[None][chore] Early emission of first response with overlap scheduling - redo
#14209 opened May 17, 2026 by brb-nv Collaborator • Draft
1 task done
@brb-nv
2
[None][chore] Early emission of responses with overlap scheduling
#14208 opened May 17, 2026 by brb-nv Collaborator • Draft
1 task done
@brb-nv
5
[None][chore] Refactor handle_responses() to smaller functions
#14207 opened May 16, 2026 by brb-nv Collaborator • Draft
1 task done
@brb-nv
6
[None][chore] log KV cache utilization and context tokens per iter
#14206 opened May 16, 2026 by pcicotti Collaborator Loading…
1 task done
@pcicotti
4
[None][test] Waive 4 failed cases for main in QA CI
#14205 opened May 16, 2026 by xinhe-nv Collaborator • Draft
@xinhe-nv
@coderabbitai
#14203 opened May 16, 2026 by hnover-nv Collaborator • Draft
1 task done
@hnover-nv
3
[#13816][feat] AutoDeploy: Optimize gpt-oss-120b perf
#14202 opened May 16, 2026 by taylor-yb-lee Collaborator • Draft
1 task
@taylor-yb-lee
[https://nvbugs/6018046][fix] Drop max_batch_size 32→8 for throughput_pp4_mtp (matching throughput_bs8_mtp), l
#14201 opened May 16, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@tensorrt-cicd
1
[None][feat] Enable sliding window attention for eagle3 Community want to contribute PRs initiated from Community
#14200 opened May 16, 2026 by murphymatt Loading…
1 task done
@murphymatt
1
[None][bug] NVFP4 MoE: requantize w1/w3 when global scales differ Community want to contribute PRs initiated from Community
#14199 opened May 16, 2026 by johnheo Loading…
3 tasks
@johnheo
3
(DO NOT SUBMIT) WideEP FT MVP prorotype
#14198 opened May 16, 2026 by chienchunhung Collaborator • Draft
1 task
@chienchunhung
[TRTLLM-12706][perf] Optimize beam search candidate reconstruction by skipping prompt-prefix copies
#14197 opened May 15, 2026 by xuanzic Collaborator Loading…
1 task done
@xuanzic
9
[https://nvbugs/6099723][fix] Keep MNNVL fix; add SM120/121-conditional override in pytorch_model_config.py th
#14196 opened May 15, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@tensorrt-cicd @ziyixiong-nv
1
[None][doc] Update spec dec support matrices
#14195 opened May 15, 2026 by mikeiovine Collaborator Loading…
1 task done
@mikeiovine
4
[#12702][feat] Autodeploy deprecate the legacy triton attention
#14194 opened May 15, 2026 by nvchenghaoz Collaborator Loading…
1 task done
@nvchenghaoz
8
[None][fix] Add SPDX Apache-2.0 headers to auto_deploy test files
#14193 opened May 15, 2026 by bmarimuthu-nv Collaborator Loading…
1 task done
@bmarimuthu-nv
1
[https://nvbugs/6133201][fix] Bump GEN max_num_tokens in disagg perf YAMLs
#14191 opened May 15, 2026 by xwang233 Collaborator Loading…
1 task done
@xwang233
7
[None][test] Add CUTLASS variant to V4-Flash EPLB accuracy tests
#14190 opened May 15, 2026 by Tabrizian Member Loading…
1 task done
@Tabrizian
3
Beam search logits processor v2 Community want to contribute PRs initiated from Community
#14189 opened May 15, 2026 by kyurious-george Loading…
1 task
@kyurious-george
3
[Trigger CI only, don't merge]Try unwaive 6029882 to reproduce the failure.
#14188 opened May 15, 2026 by SimengLiu-nv Collaborator • Draft
1 task done
@SimengLiu-nv
3
[https://nvbugs/5981293][fix] Lower GSM8K reference for the NVFP4 + MTP + FP8 KV variant from 88.2 to 70.0 (th
#14187 opened May 15, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@QiJune @tensorrt-cicd
1
[TRTLLMINF-76][feat] Delegate runKubernetesPodWithInfraRetry to shared lib
#14186 opened May 15, 2026 by dpitman-nvda Collaborator Loading…
1 task
@dpitman-nvda
2
[https://nvbugs/6162128][tests] Skip nano v3 E2E tests entirely on G/B300
#14185 opened May 15, 2026 by 2ez4bz Collaborator Loading…
1 task done
@2ez4bz
8
[https://nvbugs/6179555][fix] Lower the NVFP4 GSM8K reference for nvidia/Nemotron-3-Nano from 67.286 to 66.5 s
#14184 opened May 15, 2026 by tensorrt-cicd Collaborator Loading…
2 tasks done
@QiJune @tensorrt-cicd
1
ProTip! Mix and match filters to narrow down what you’re looking for.