Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
498 Open 7,237 Closed
498 Open 7,237 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

add fifo v2 for helix
#11433 opened Feb 10, 2026 by brb-nv • Draft
1 task
[#10243][feat] Draft - DONT REVIEW - Add TRT-LLM attention backend with hybrid model support to AutoDeploy
#11430 opened Feb 10, 2026 by MrGeva Loading…
1 task
18
[None][feat] AutoDeploy: Add nemotron v2 acc test
#11429 opened Feb 10, 2026 by nvchenghaoz Loading…
1 task
1
[None][fix] Nemotron Super fix
#11425 opened Feb 10, 2026 by IzzyPutterman Loading…
1 task done
6
draft AD skill
#11420 opened Feb 10, 2026 by galagam • Draft
[https://nvbugs/5832481][test] Add gpt-oss-120b-Eagle3-throughput case on DGX-Spark
#11419 opened Feb 10, 2026 by JennyLiu-nv Loading…
1 task done
4
fix(moe): enable fused routing kernel for single-group MoE configs (D…
#11418 opened Feb 10, 2026 by kaiyux • Draft
1 task
[https://nvbugs/5809169][unwaive] Unwaive TestGPTOSS test
#11417 opened Feb 10, 2026 by peaceh-nv Loading…
[https://nvbugs/5809169][unwaive] Unwaive TestGPTOSS test
#11416 opened Feb 10, 2026 by peaceh-nv Loading…
1
[https://nvbugs/5624818][fix] Add unittest for GPT-OSS non-paged_context_fmha
#11415 opened Feb 10, 2026 by pengbowang-nv • Draft
1 task done
3
[#11109][feat] AutoDeploy: GLM 4.7 Flash Improvements
#11414 opened Feb 10, 2026 by bmarimuthu-nv Loading…
1 task done
14
[https://nvbugs/5880261][fix] fix cacheTransceiver
#11409 opened Feb 10, 2026 by chuangz0 Loading…
1 task done
7
[None][chore] Merge residual+hidden into layer norm at the end of each MTP, and remove a % operation
#11406 opened Feb 10, 2026 by hnover-nv Loading…
4
[TRTLLM-10329][feat] Fix weight loading for Nemotron 3 models on DGX Spark
#11405 opened Feb 10, 2026 by pamelap-nvidia Loading…
1 task done
11
[None][chore] Fix gpu memory requirement in stress test
#11404 opened Feb 10, 2026 by dominicshanshan Loading…
1 task done
4
[None][fix] Fix silent MPI failures on models with custom tokenizers
#11399 opened Feb 10, 2026 by jthomson04 Loading…
1 task done
14
[TRTLLM-10948][feat] Add GPU energy monitoring to trtllm-bench Community want to contribute PRs initiated from Community
#11397 opened Feb 10, 2026 by inciaf Loading…
1 task
6
[https://nvbugs/5868038][fix] Gracefully terminate disagg serving servers to prevent leftover subprocess warnings
#11395 opened Feb 9, 2026 by peihu-nv Loading…
1 task done
10
[][feat] AutoDeploy : Support Qwen3.5
#11394 opened Feb 9, 2026 by bmarimuthu-nv • Draft
1 task
3
[None][chore] Add failed cases into waives.txt
#11392 opened Feb 9, 2026 by xinhe-nv Loading…
25
[None][feat] Integrate all reduce from flashinfer
#11391 opened Feb 9, 2026 by NVShreyas Loading…
1 task done
20
[None][fix] numpy v2 preparations
#11389 opened Feb 9, 2026 by Funatiq • Draft
1 task done
15
[https://nvbugs/5823783][fix] Fix multi-node trust_remote_code hang i…
#11383 opened Feb 9, 2026 by JunyiXu-nv Loading…
1 task done
7
[None][feat] Remove non flash attetnion style fmha_v2 kernel for hopper
#11381 opened Feb 9, 2026 by pengbowang-nv • Draft
1 task done
11
[TRTLLM-9644][infra] Implement isolation for slurm
#11380 opened Feb 9, 2026 by EmmaQiaoCh • Draft
1 task done
10
ProTip! Mix and match filters to narrow down what you’re looking for.