Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
459 Open 5,689 Closed
459 Open 5,689 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-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences.
#9524 opened Nov 27, 2025 by lfr-0531 • Draft
1 task
[None][chore] Weekly mass integration of release/1.1 -- rebase
#9522 opened Nov 27, 2025 by dominicshanshan Loading…
1 task done
6
[None][fix] Pass checkpoint_format to create_input_processor
#9521 opened Nov 27, 2025 by Funatiq • Draft
1 task
2
[TRTLLM-9242][doc] Add examples showcasing openai compatible APIs
#9520 opened Nov 27, 2025 by JunyiXu-nv Loading…
1 task done
13
[https://nvbugs/5652062][fix] Rectify the checking rule for finishing a request
#9516 opened Nov 27, 2025 by ziyixiong-nv Loading…
1 task
5
[https://nvbugs/5680133][fix] Implement customizable router for cutlass MoE during autotuning
#9515 opened Nov 27, 2025 by hyukn • Draft
1 task done
3
[None] [feat] add eos_token_id in generation_config to sampling params
#9514 opened Nov 27, 2025 by JadoTu Loading…
1 task done
4
[None][infra] Test block nodes
#9513 opened Nov 27, 2025 by EmmaQiaoCh • Draft
1 task
5
[https://nvbugs/5666804][test] only adding sampler config for limited models
#9512 opened Nov 27, 2025 by ruodil Loading…
1 task done
@ruodil
5
[https://nvbugs/5527655][test] Add test case for RCCA 5527655
#9511 opened Nov 27, 2025 by fredricz-20070104 Loading…
5
[None][feat] update trtllm-gen nvfp4 kernels with better performance
#9510 opened Nov 27, 2025 by PerkzZheng Loading…
1 task done
9
[None][fix] Introduce inline namespace to avoid symbol collision
#9509 opened Nov 27, 2025 by yihwang-nv Loading…
3
[https://nvbugs/5422621][test] Add GB 200 WIDEEP test case for RCCA 5422621
#9506 opened Nov 27, 2025 by fredricz-20070104 Loading…
4
[#9150][feat] AutoDeploy Nemotron-Flash support
#9504 opened Nov 26, 2025 by lucaslie Loading…
1 task done
1
30
feat: Cohere2ForCausalLM support (Command-A, Command-R7B) Community want to contribute PRs initiated from Community
#9501 opened Nov 26, 2025 by jkbeavers Loading…
7
[None][feat] AutoDeploy: Use the router gemm op for nemotron MOE
#9500 opened Nov 26, 2025 by nvchenghaoz Loading…
@nvchenghaoz
4
[TRTC-1975] [feat] BREAKING: Enable chunked prefill by default
#9499 opened Nov 26, 2025 by venkywonka • Draft
1 task
@venkywonka
5
[#9496][fix] AutoDeploy: remove auto-tuner from nvfp4_gemm forward
#9497 opened Nov 26, 2025 by nzmora-nvidia Loading…
1 task done
4
[None][infra] add attribution files for release/1.1
#9495 opened Nov 26, 2025 by yuanjingx87 Loading…
1 task done
3
[None][perf] Helix: improve all-to-all perf for large CP size
#9494 opened Nov 26, 2025 by MatthiasKohl Loading…
1 task done
5
[None] [chore] Clean up slurm script logics
#9493 opened Nov 26, 2025 by kaiyux Loading…
1 task done
9
[None][infra] Move some of the tests from b200 to gb200 to avoid load model issue
#9492 opened Nov 26, 2025 by yizhang-nv Loading…
1 task done
15
[None][fix] Correct virtual memory allocation alignment
#9491 opened Nov 26, 2025 by tongyuantongyu Loading…
1 task done
5
[None][fix] Fix unterminated process issue for RemoteOpenAIServer
#9490 opened Nov 26, 2025 by JunyiXu-nv Loading…
1 task done
4
[TRTLLM-8958][feat] and [TRTLLM-8960]: create ConfigurableMoE and support TRTLLMGenFusedMoE as backend
#9486 opened Nov 26, 2025 by xxi-nv Loading…
1 task done
53
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.