Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
382 Open 4,354 Closed
382 Open 4,354 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][fix] api stability bug in status label Release Blocker PRs that blocking the final release build or branching out the release branch
#7861 opened Sep 19, 2025 by Superjomn Loading…
1 task done
4
[None] Update benchmark script
#7860 opened Sep 19, 2025 by zerollzeng Loading…
1 task
Disable GC on disagg server and client
#7858 opened Sep 19, 2025 by yuantailing Loading…
1 task
4
[https://nvbugs/5477404][chore] unwaive test_disaggregated_single_gpu.py::test_disaggregated_llama_context_capacity
#7857 opened Sep 19, 2025 by reasonsolo Loading…
1 task done
3
[None][fix] fix trtllm-gen moe backend on blockwise fp8 ckpt (Qwen3-235B-A22B-FP8)
#7856 opened Sep 19, 2025 by jhaotingc • Draft
1 task
1
[https://nvbugs/5525849][fix] Cherry-pick to fix mismatch of max seq len between kv cache manager and dummy requests Cherry-pick It's a label that applies to Cherry-pick PR.
#7855 opened Sep 19, 2025 by HuiGao-NV Loading…
1 task
9
[None][fix] cherrypick to main: Fix possible mpi broadcast and gather issue on large object Cherry-pick It's a label that applies to Cherry-pick PR.
#7854 opened Sep 19, 2025 by dongxuy04 Loading…
1 task done
4
[None][ci] Waive llama3 auto dtype test bug in https://nvbugs/5527956.
#7853 opened Sep 19, 2025 by dominicshanshan Loading…
1 task done
4
[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code.
#7851 opened Sep 19, 2025 by nv-guomingz Loading…
1 task
7
[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the …
#7850 opened Sep 19, 2025 by nv-guomingz Loading…
1 task
3
[https://nvbugs/5521799][fix] Trim incorrectly generated harmony messages
#7849 opened Sep 19, 2025 by JunyiXu-nv Loading…
1 task done
11
[None][doc] Update Perf-Overview.md for release/1.0
#7848 opened Sep 18, 2025 by zbpatel Loading…
1 task
8
[None][doc] Added line about partial reuse
#7846 opened Sep 18, 2025 by thorjohnsen Loading…
4
[https://nvbugs/5522462][fix] Fix FP8 scout illegal memory access
#7845 opened Sep 18, 2025 by mikeiovine Loading…
1 task done
6
[#4674][bugfix] AutoDeploy Fix memory leak in fuse_moe
#7844 opened Sep 18, 2025 by galagam • Draft
1 task
4
[AutoDeploy] Linear Attention Support
#7843 opened Sep 18, 2025 by lucaslie • Draft
1 task
[None][chore] Add failed cases into waives.txt
#7841 opened Sep 18, 2025 by xinhe-nv Loading…
9
[TRTLLM-8188][chore] refactor GenerationExecutorWorker with WorkerBase for better code reusing
#7840 opened Sep 18, 2025 by Superjomn Loading…
1 task done
23
[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSe…
#7838 opened Sep 18, 2025 by liji-nv Loading…
1 task
7
[None][doc] scaffolding tech blog part one
#7835 opened Sep 18, 2025 by WeiHaocheng Loading…
1 task
20
[None][chore] remove cli cases for rtx6k
#7833 opened Sep 18, 2025 by crazydemo Loading…
1 task done
6
[TRTLLM-8031][feat] Add chunked return_generation_logits logic
#7831 opened Sep 18, 2025 by yibinl-nvidia • Draft
1 task
3
[None][fix] refine backend option handling for commands
#7829 opened Sep 18, 2025 by tongyuantongyu Loading…
1 task done
8
[https://nvbugs/5512556][unwaive] Unwaive DeepSeek PP tests
#7828 opened Sep 18, 2025 by peaceh-nv Loading…
1 task
4
Rpc.rebase
#7827 opened Sep 18, 2025 by Superjomn • Draft
1 task
27
ProTip! Mix and match filters to narrow down what you’re looking for.