Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
984 Open 12,151 Closed
984 Open 12,151 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 one-model MTP KV cache accounting
#17264 opened Aug 4, 2026 by 2ez4bz Collaborator Loading…
1 task done
@2ez4bz
6
[TRTLLMINF-237][infra] Re-home L0_Test SLURM finalizer
#17263 opened Aug 4, 2026 by dpitman-nvda Collaborator Loading…
1 task done
@dpitman-nvda
5
[TRTLLM-13767][feat] integrate FP4 Conv3d into parallel Wan VAE VisualGen
#17262 opened Aug 4, 2026 by taianz-nv Collaborator • Draft
@taianz-nv
[https://nvbugs/6550276][fix] Clamp residency to what the quota affords (allreduce-MIN across ranks) behind…
#17261 opened Aug 4, 2026 by trtllm-agent Collaborator Loading…
2 tasks done
@VALLIS-NERIA @trtllm-agent
5
[None][feat] DONT REVIEW glm image support VisualGen
#17260 opened Aug 4, 2026 by yibinl-nvidia Collaborator • Draft
1 task
@yibinl-nvidia
[None][fix] Skip no-op MXFP4 weight padding
#17259 opened Aug 4, 2026 by jiaganc Collaborator • Draft
1 task done
@jiaganc
[None][perf] DeepSeek-V4: cut host overhead in generation-phase metadata preparation
#17257 opened Aug 4, 2026 by hyukn Collaborator • Draft
@hyukn
8
[TRTLLMINF-40][fix] Throw typed InfraFailure when SLURM submission yields no job ID
#17255 opened Aug 4, 2026 by brnguyen2 Collaborator Loading…
3 tasks done
@brnguyen2
27
[TRTLLM-14831][chore] Consolidate package bootstrap and relocate restricted deserialization
#17254 opened Aug 4, 2026 by YihuiLu512 Collaborator Loading…
1 task done
@YihuiLu512
9
[None][infra] CBTS code coverage date early save
#17253 opened Aug 4, 2026 by crazydemo Collaborator Loading…
1 task done
@crazydemo
14
[None][test] Remove two GPT-OSS tests from GB200 pre-merge
#17252 opened Aug 4, 2026 by yizhang-nv Member Loading…
1 task done
@yizhang-nv
4
[None][infra] Align VisualGen CBTS rule with CODEOWNERS scope
#17251 opened Aug 4, 2026 by crazydemo Collaborator • Draft
1 task done
@crazydemo
[None][chore] Fix guardword
#17250 opened Aug 4, 2026 by tongyuantongyu Member Loading…
1 task done
@tongyuantongyu
4
[None][doc] Explain benchmark output token length
#17249 opened Aug 4, 2026 by zcxGGmu Loading…
@zcxGGmu
4
[TRTLLMINF-240][infra] L0 job enhancement for automatic nightly release
#17248 opened Aug 4, 2026 by niukuo Collaborator Loading…
1 task done
@niukuo
11
[None][fix] Announce MTP shapes to attention metadata in layer-wise benchmarks
#17247 opened Aug 4, 2026 by dc3671 Collaborator Loading…
1 task done
@dc3671
6
[None][doc] Clarify KV cache host offload limits
#17246 opened Aug 4, 2026 by zcxGGmu Loading…
@zcxGGmu
4
[None][doc] Document TensorRT LLM binary compatibility
#17244 opened Aug 4, 2026 by zcxGGmu Loading…
@zcxGGmu
3
[https://nvbugs/6545424][perf] Enable Qwen3.5 fused ops under torch.c…
#17243 opened Aug 4, 2026 by liji-nv Collaborator Loading…
1 task done
@liji-nv
8
[None][fix] Use IPC-shareable KV bounce buffers on non-fabric platforms
#17241 opened Aug 4, 2026 by erictsai-nv Contributor • Draft
1 task done
@erictsai-nv
2
[None][perf] Autotune large-M MXFP8 GEMM tactics
#17238 opened Aug 4, 2026 by peihu-nv Collaborator Loading…
2 tasks done
@peihu-nv
4
[None][perf] Use FlashInfer MXFP8 GEMM for MiniMax-M3 decode
#17237 opened Aug 4, 2026 by peihu-nv Collaborator Loading…
1 task done
@peihu-nv
12
[None][perf] Fuse MiniMax-M3 MSA block selection
#17236 opened Aug 4, 2026 by peihu-nv Collaborator Loading…
1 task done
@peihu-nv
5
[None][doc] Add trtllm-bench LWS launch guidance
#17235 opened Aug 4, 2026 by zcxGGmu Loading…
@zcxGGmu
5
[https://nvbugs/6525008][fix] Isolate FlashInfer JIT workspaces for MPI workers
#17233 opened Aug 4, 2026 by VALLIS-NERIA Collaborator Loading…
1 task done
@VALLIS-NERIA
28
ProTip! Exclude everything labeled bug with -label:bug.