Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
306 Open 2,539 Closed
306 Open 2,539 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

[fix] improve fp4_block_scale_moe_runner type check Community Engagement help/insights needed from community Community want to contribute PRs initiated from Community
#5681 opened Jul 2, 2025 by Alcanderian Loading…
1
chore: update doc by replacing use_cuda_graph with cuda_graph_config
#5680 opened Jul 2, 2025 by nv-guomingz Loading…
2
refactor: decoding inputs
#5679 opened Jul 2, 2025 by Funatiq • Draft
3
[Infra][TRTLLM-6224] - Upgrade dependencies to DLFW 25.06 and CUDA 12…
#5678 opened Jul 2, 2025 by yiqingy0 • Draft
2
[TRTLLM-6100] fix: Nvbug 5356427: autotuned TRTLLM Gen fp8 block scale MoE illegal memory access bug Something isn't working
#5676 opened Jul 2, 2025 by DomBrown Loading…
@DomBrown
21
MTP and derivatives: Align sample state with trtllm sampler sample state
#5675 opened Jul 2, 2025 by netanel-haber Loading…
@dcampora @byshiue @Funatiq
8
[Infra] - Waive failed cases on release/0.21
#5674 opened Jul 2, 2025 by EmmaQiaoCh Loading…
6
Fix rerun step
#5672 opened Jul 2, 2025 by yiqingy0 • Draft
3
[Infra] - Waive failed tests for main 0702
#5671 opened Jul 2, 2025 by EmmaQiaoCh Loading…
6
fix: Fix missing arg to alltoall_prepare_maybe_dispatch
#5669 opened Jul 2, 2025 by syuoni Loading…
4
[TRTLLM-5966][feat] Initial steps towards Helix parallelism support
#5668 opened Jul 2, 2025 by MatthiasKohl Loading…
13
chore: Remove unused isFullContextRequest method
#5666 opened Jul 2, 2025 by Funatiq Loading…
12
fix [nvbug5351244]: address remote mpi session submit
#5664 opened Jul 2, 2025 by Superjomn Loading…
12
feat: Enable alltoall for Cutlass MoE Backend
#5663 opened Jul 2, 2025 by bobboli • Draft
add supported models doc
#5662 opened Jul 2, 2025 by QiJune Loading…
5
fix: Set init value for moe expert id
#5660 opened Jul 2, 2025 by WeiHaocheng Loading…
@WeiHaocheng
12
Avoiding the kernel launch if no finished context requests
#5659 opened Jul 1, 2025 by rakib-hasan Loading…
10
[None][infra] Update the auto-community label action to be triggered every hour
#5658 opened Jul 1, 2025 by poweiw • Draft
test: Validate and add accuracy& perf tests for Ministral-8B-Instruct[-FP8](pytorch only)
#5654 opened Jul 1, 2025 by venkywonka • Draft
5 of 7 tasks
5
[NVBUG:5355009] Modify check for fuse_fp4_quant on SM120
#5651 opened Jul 1, 2025 by farazkh80 Loading…
21
[feat] Add TensorRT-Engine Qwen3 model support Community Engagement help/insights needed from community Community want to contribute PRs initiated from Community
#5650 opened Jul 1, 2025 by gkswns0531 Loading…
Refactor the control message transceiver with ZeroMQ
#5647 opened Jul 1, 2025 by Shunkangz • Draft
@Shunkangz
[TRTLLM-4923][feat] Enable CUDA graphs for Nemotron-H
#5646 opened Jul 1, 2025 by tomeras91 Loading…
24
chore: bump version to 1.0.0rc2
#5645 opened Jul 1, 2025 by yiqingy0 • Draft
3
[Draft] feat: Add phi-4-multimodal pytorch-backend support
#5644 opened Jul 1, 2025 by Wanli-Jiang • Draft
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.