Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
516 Open 7,166 Closed
516 Open 7,166 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

[TRTLLM-10927][perf] Use NCCL LSA Barrier to implement synchronization for NVLinkOneSided AlltoAll kernels.
#11366 opened Feb 8, 2026 by bobboli • Draft
1 task
[None][chore] update model list
#11364 opened Feb 8, 2026 by tcherckez-nvidia Loading…
1 task done
5
[None][chore] Add failed cases into waives.txt
#11363 opened Feb 8, 2026 by xinhe-nv • Draft
[None][Perf] Multi-stream attention, fuse rmsnorm add, fuse swiglu
#11362 opened Feb 8, 2026 by suyoggupta Loading…
1 task
21
[TRTLLM-8263][feat] Add ctx-only and gen-only Disagg Perf Tests
#11361 opened Feb 7, 2026 by chenfeiz0326 Loading…
1 task
8
[TRTC-265][chore] Add CODEOWNERS coverage for serve/ and commands/ directories
#11359 opened Feb 7, 2026 by venkywonka Loading…
1 task done
@venkywonka
3
[TRTC-264][doc] Add CLAUDE.md and AGENTS.md
#11358 opened Feb 7, 2026 by venkywonka Loading…
1 task done
@venkywonka
10
# TensorRT-LLM: Enable Jetson Thor (sm_110) Support & Build Fixes Community want to contribute PRs initiated from Community
#11357 opened Feb 6, 2026 by cjac • Draft
1 task
2
[Draft] AutoDeploy GLM4.7 flash bundle
#11356 opened Feb 6, 2026 by bmarimuthu-nv Loading…
1 task done
14
[#11146][feat] AutoDeploy: Add triton paged attention
#11355 opened Feb 6, 2026 by nvchenghaoz • Draft
1 task
8
[https://nvbugs/5829097][fix] Disaggregated serving: Only send finished context requests to the KV cache transceiver
#11354 opened Feb 6, 2026 by Funatiq Loading…
1 task done
7
[#11109][feat] AutoDeploy: GLM 4.7 Flash Improvements
#11351 opened Feb 6, 2026 by lucaslie • Draft
1 task done
@bmarimuthu-nv
3
Remove mem est 2
#11350 opened Feb 6, 2026 by HuiGao-NV • Draft
1 task
31
[TRTLLM-10030][perf] avoid syncs in beam search + other improvements
#11349 opened Feb 6, 2026 by ixlmar Loading…
1 task done
10
[TRTLLM-1234][feat] Fixed sharding for shared embedding projections
#11348 opened Feb 6, 2026 by greg-kwasniewski1 Loading…
1 task done
1
26
[TRTLLM-9904][feat] KVCache V2 MTP support
#11346 opened Feb 6, 2026 by liji-nv Loading…
1 task done
14
[None][feat] Optimize mamba2 _chunk_scan_fwd_kernel
#11345 opened Feb 6, 2026 by JadoTu Loading…
1 task done
4
[None][feat] Optimize the q3n decode kernel with IO read
#11344 opened Feb 6, 2026 by JadoTu Loading…
1 task done
4
[None][feat] Optimize superv3 nvfp4 for better perf version3
#11343 opened Feb 6, 2026 by Wanli-Jiang • Draft
1 task
[None][feat] Refactor time breakdown tool (visualization, generation breakdown, etc.)
#11340 opened Feb 6, 2026 by luyiyun1021 Loading…
1 task done
7
[https://nvbugs/5866619][fix] Support PEFT-saved safetensors file loading
#11339 opened Feb 6, 2026 by Wanli-Jiang Loading…
1 task done
1
Sg/ll/glm4 7 flash rebased
#11338 opened Feb 6, 2026 by suyoggupta • Draft
1 task
[TRTLLM-10866][feat] implement disaggregated harmony chat
#11336 opened Feb 6, 2026 by reasonsolo Loading…
1 task done
16
[None][chore] Reduce attention module repeated warnings.
#11335 opened Feb 6, 2026 by yuxianq Loading…
1 task done
8
[None][feat] Use new index api, add block scale support, fix max_seq_len esitmation, add flash mla support
#11334 opened Feb 6, 2026 by yizhang-nv Loading…
1 task done
15
ProTip! Updated in the last three days: updated:>2026-02-05.