Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
660 Open 8,221 Closed
660 Open 8,221 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][doc] Blog19 for DWDP.
#12725 opened Apr 3, 2026 by wanqian-nv • Draft
1 task
@wanqian-nv
4
[https://nvbugs/5849648][fix] Fix GPTOSS Chat Template for Disagg Tests
#12724 opened Apr 3, 2026 by dongfengy Loading…
1 task done
@dongfengy
3
[https://nvbugs/6043312][fix] fix_mooncake_transfer_agent_binding
#12723 opened Apr 3, 2026 by chuangz0 Loading…
1 task done
@chuangz0
5
[None][feat] optimize ucx build connection
#12722 opened Apr 3, 2026 by chuangz0 Loading…
1 task done
@chuangz0
6
DO NOT REVIEW[None][chore] Dummy change to trigger build
#12721 opened Apr 3, 2026 by longlee0622 Loading…
1 task
@longlee0622
3
[None][docs] Blog 19: GVR Top-K for Blackwell
#12720 opened Apr 3, 2026 by longcheng-nv • Draft
@longcheng-nv
[None][feat] Add per-request stream_interval support Community want to contribute PRs initiated from Community
#12719 opened Apr 3, 2026 by quan-deepinfra Loading…
4 tasks done
@quan-deepinfra
3
[https://nvbugs/6043291][fix] Add fatal error detection to prevent zombie worker pods
#12718 opened Apr 2, 2026 by chienchunhung • Draft
1 task
@chienchunhung
2
[https://nvbugs/5941242][fix] Fix SigLIP test failure
#12717 opened Apr 2, 2026 by tijyojwad Loading…
1 task done
@tijyojwad
10
[None][feat] AutoDeploy: Add Gemma4 Support
#12710 opened Apr 2, 2026 by bmarimuthu-nv Loading…
@bmarimuthu-nv
8
[https://nvbugs/5962106][fix] Exclude NCCL_SYMMETRIC from allreduce auto-tuner tactics
#12709 opened Apr 2, 2026 by nv-lschneider Loading…
1 task done
@nv-lschneider
9
[#12712][feat] AutoDeploy Model Onboarding Sprint 03/19 - Part 1 (infra only)
#12708 opened Apr 2, 2026 by govind-ramnarayan Loading…
1 task done
1
@govind-ramnarayan
13
[None][fix] Enable CUDA core fast path for SM121 (DGX Spark) Community want to contribute PRs initiated from Community
#12705 opened Apr 2, 2026 by mihai-chiorean Loading…
1 of 2 tasks
1
[#11932][fix] Filter CUTLASS MoE GEMM tile configs by device shared memory on SM121 Community want to contribute PRs initiated from Community
#12704 opened Apr 2, 2026 by mihai-chiorean Loading…
3 tasks done
@mihai-chiorean
5
[None][feat] Add simulation mode for serving benchmarking
#12700 opened Apr 2, 2026 by venkywonka • Draft
4 tasks
@venkywonka
[#12632][feat] Initial prototype for AutoDeploy compile cache
#12698 opened Apr 2, 2026 by nvchenghaoz • Draft
1 task
@nvchenghaoz
5
[https://nvbugs/6029864][fix] Fix flaky ray test failure
#12697 opened Apr 2, 2026 by brb-nv Loading…
1 task done
@brb-nv
4
[None][feat] Add radix tree cache priority boost and store chunked context blocks
#12696 opened Apr 2, 2026 by lancelly • Draft
@lancelly
1
[None][doc] add attention developer guide
#12693 opened Apr 2, 2026 by QiJune Loading…
1 task
@QiJune
8
[https://nvbugs/5983390][perf] Reduce host overhead in DSA MLA attention path
#12691 opened Apr 2, 2026 by liji-nv Loading…
1 task done
@liji-nv
1
[None][fix] Fix CuteDslFusedMoE.load_weights signature to accept allow_partial_loading
#12690 opened Apr 2, 2026 by tianyuz-nv Loading…
@tianyuz-nv
15
[TRTLLM-9523][chore] e2e tests for KV manager v2 with dis-agg
#12689 opened Apr 2, 2026 by Shixiaowei02 Loading…
1 task done
@Shixiaowei02 @chuangz0
6
[None][infra] Add DSV32 Disagg Perf Tests Back
#12688 opened Apr 2, 2026 by chenfeiz0326 Loading…
1 task done
@chenfeiz0326
4
[None][fix] Remove clone in fp8 quant.
#12687 opened Apr 2, 2026 by Tracin Loading…
1 task done
@Tracin
8
[None][feat] Optimize MoE DenseGEMM FC2 kernel
#12686 opened Apr 2, 2026 by mingyangHao • Draft
1 task done
ProTip! no:milestone will show everything without a milestone.