Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
396 Open 4,818 Closed
396 Open 4,818 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][chore] Remove duplicate log outputs in test_perf.py
#8418 opened Oct 16, 2025 by hyukn Loading…
1 task done
4
[None][chore] replace print_colored_debug with logger_debug
#8417 opened Oct 16, 2025 by Superjomn Loading…
1 task done
8
[TRTLLM-8638][fix] waive llam4 tests on H20
#8416 opened Oct 16, 2025 by xinhe-nv Loading…
1 task done
6
[None][chore] Align RPC performance with existing GenerationExecutor
#8415 opened Oct 16, 2025 by Superjomn Loading…
1 task
2
[https://nvbugs/5501820][fix] Add requirements for numba-cuda version to WAR mem corruption (#7992)
#8414 opened Oct 16, 2025 by pengbowang-nv • Draft
1 task
8
[None][bug] Set NCCL_GRAPH_REGISTER to false to avoid hang
#8413 opened Oct 16, 2025 by Tabrizian Loading…
1 task done
3
[TRTLLM-8480][chore] clean create_py_executor API
#8412 opened Oct 16, 2025 by QiJune Loading…
1 task done
10
[https://nvbugs/5451280][fix] Reduce memory fraction problem by warmu…
#8410 opened Oct 16, 2025 by liji-nv Loading…
1 task done
7
[None][bug] Set NCCL_GRAPH_REGISTER to false to avoid hang
#8409 opened Oct 16, 2025 by Tabrizian Loading…
1 task done
5
[https://nvbugs/5496705][fix] Fix high IPC overhead with logprobs enabled by removing duplicate sends
#8406 opened Oct 16, 2025 by nvxuanyuc Loading…
4
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 GEMM + BF16 KV cache
#8405 opened Oct 16, 2025 by chang-l • Draft
1 task done
[None][infra] Update CI allowed list 2025_10_15
#8403 opened Oct 15, 2025 by yuanjingx87 Loading…
1 task
2
[None][feat] Update load_weights method to include mapping parameter in checkpoint loaders
#8402 opened Oct 15, 2025 by Funatiq • Draft
1 task
3
[https://nvbugs/5502901][fix] Set max_seq_len and max_batch_size in TestNemotronUltra test cases to prevent OOM
#8399 opened Oct 15, 2025 by amitz-nv Loading…
1 task
@amitz-nv
4
[TRTLLM-8436][feat] batched sampling and top-k logprobs improvements
#8398 opened Oct 15, 2025 by ixlmar • Draft
1 task done
8
[https://nvbugs/5437384][test] fix trtllm-llmapi-launch multi tests with single launch
#8397 opened Oct 15, 2025 by Superjomn Loading…
1 task done
17
[None][chore] Cleanup KV cache manager
#8396 opened Oct 15, 2025 by Funatiq • Draft
1 task
4
[none][feat] Support nano-v2-vlm with multiple PRs
#8395 opened Oct 15, 2025 by Wanli-Jiang • Draft
[TRTLLM-8669][infra] Use artifactory mirror for install python
#8394 opened Oct 15, 2025 by ZhanruiSunCh Loading…
1 task
9
[None][feat] Add fmha_v2 kernel for head_dim=80 and sm=100 to support VLM
#8392 opened Oct 15, 2025 by Wanli-Jiang Loading…
1 task done
11
[https://nvbugs/5540138][fix] Fix shape error when duplicating kv.
#8390 opened Oct 15, 2025 by Tracin Loading…
1 task
9
[None][fix] improve mpirun hang issues
#8385 opened Oct 15, 2025 by xinhe-nv • Draft
1 task
Ampere xqa swa specdec
#8383 opened Oct 15, 2025 by jhaotingc Loading…
1 task
4
[TRTLLM-8464][infra] Use public triton 3.5.0
#8382 opened Oct 15, 2025 by ZhanruiSunCh Loading…
1 task
11
[None][fix] fix error when processing batches containing both text and mm data Community want to contribute PRs initiated from Community
#8381 opened Oct 15, 2025 by Nekofish-L Loading…
1 task done
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.