Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
455 Open 5,891 Closed
455 Open 5,891 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][feat] AutoDeploy: prepare_metadata revisited
#9764 opened Dec 7, 2025 by lucaslie • Draft
1 task
@lucaslie
Modified openai_server.py file to have control over KV cache memory size.
#9763 opened Dec 6, 2025 by AzizulZahid Loading…
1 task
[#9760][fix] Use RequestError for validation errors to prevent engine shutdown Community want to contribute PRs initiated from Community
#9761 opened Dec 6, 2025 by tzulingk Loading…
1
9
User/brb/validate mapping combinations
#9759 opened Dec 6, 2025 by brb-nv • Draft
1 task
[WIP] EPD qwen2.5 VL
#9758 opened Dec 6, 2025 by 2ez4bz • Draft
1 task
8
[TRTLLM-5972][chore] Load balance decode token KV cache with helix parallelism
#9757 opened Dec 5, 2025 by brb-nv Loading…
1 task done
9
[#9753][feat] AutoDeploy: Implement add rms_norm fusion
#9754 opened Dec 5, 2025 by nvchenghaoz Loading…
14
[WIP] Replace patches with custom model implementation
#9751 opened Dec 5, 2025 by 2ez4bz • Draft
1 task
[None][feat] Draft: Eagle + Medusa
#9748 opened Dec 5, 2025 by IzzyPutterman Loading…
1 task
4
[None][feat] AutoDeploy: hidden state capture mechanis AutoDeploy <NV> AutoDeploy Backend
#9747 opened Dec 5, 2025 by lucaslie • Draft
1 task
@lucaslie
2
[None] Fix warning when capturing CUDA graph
#9746 opened Dec 5, 2025 by ziyixiong-nv Loading…
1 task
4
[None][infra] Fail fast if SLURM entrypoint fails
#9744 opened Dec 5, 2025 by mlefeb01 Loading…
1 task
@mlefeb01
7
[None][fix] Fix two tuning cache miss issues.
#9743 opened Dec 5, 2025 by hyukn Loading…
1 task done
5
Patch Whisper BLS example Community want to contribute PRs initiated from Community
#9742 opened Dec 5, 2025 by protonicage Loading…
1 task
1
[None][test] add ntp tolerance in time metrics verification
#9741 opened Dec 5, 2025 by zhengd-nv Loading…
1 task done
5
[TRTLLM-7735][feat] Attention NVFP4 out support for torch compile
#9740 opened Dec 5, 2025 by liji-nv Loading…
1 task done
6
[None][doc] Update release notes
#9739 opened Dec 5, 2025 by QiJune Loading…
1 task
3
[None][chore] add multi-node service discovery disagg test
#9738 opened Dec 5, 2025 by reasonsolo • Draft
1 task
[TRTLLM-9717][fix] fix multi nodes tests cases
#9736 opened Dec 5, 2025 by xinhe-nv • Draft
1 task done
[None][fix] unable cuda ipc on device without nvlink (L40s) for disagg test
#9735 opened Dec 5, 2025 by chuangz0 Loading…
1 task done
4
[None][feat] update TRT-LLM Gen MoE for NvFp4 + bias with tileN=256
#9734 opened Dec 5, 2025 by nekorobov Loading…
1 task done
4
[https://nvbugs/5644632][fix] add fix_gpu_memory_fraction to disagg gptoss tests
#9732 opened Dec 5, 2025 by chuangz0 Loading…
1 task done
2
[feat][chore] Add GB300 dlcluster support since it doesn't support segment
#9731 opened Dec 5, 2025 by fredricz-20070104 Loading…
6
[https://nvbugs/5519544][feat] Adaptive number of thread workers when loading model concurrently
#9730 opened Dec 5, 2025 by jieli-matrix Loading…
1 task done
@jieli-matrix
2
[None][feat] add fp4 gemm + allreduce Community want to contribute PRs initiated from Community
#9729 opened Dec 5, 2025 by benzh-2025 Loading…
8
ProTip! no:milestone will show everything without a milestone.