Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
427 Open 4,967 Closed
427 Open 4,967 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

[feat] Use ruff for formatting and linting new files by default
#8629 opened Oct 23, 2025 by Funatiq • Draft
1 task
[TRTLLM-8832][feat] fully async _select_generated_logits with tests
#8628 opened Oct 23, 2025 by ixlmar Loading…
1 task done
10
[https://nvbugs/5508536][fix] Reintroduce: Move stop_criteria to sample_async (#7041)
#8627 opened Oct 23, 2025 by netanel-haber • Draft
[https://nvbugs/5593199][test] Enhance beam search tests deterministic dummy model
#8625 opened Oct 23, 2025 by stnie • Draft
1 task
17
[None][chore] exclude InductorSubproc from thread leak check
#8624 opened Oct 23, 2025 by leslie-fang25 Loading…
1 task done
2
Add skip condition
#8623 opened Oct 23, 2025 by suyoggupta Loading…
1 task
[None][feat] Refactor scaffolding streaming feature and fix openai wo…
#8622 opened Oct 23, 2025 by WeiHaocheng Loading…
1 task
[TRTLLM-8658][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0
#8621 opened Oct 23, 2025 by ZhanruiSunCh Loading…
1 task
[None][feat] Enable nvfp4 cuda core for sm120
#8620 opened Oct 23, 2025 by Njuapp Loading…
1 task done
1
[None][test] Clean cache for certain easily hang cases
#8619 opened Oct 23, 2025 by crazydemo Loading…
1 task done
3
[https://nvbugs/5558117][fix] Allow per-layer quant config from hf_quant_config.json
#8617 opened Oct 23, 2025 by rosenrodt Loading…
1 task done
9
Add wrapper class of tensor
#8614 opened Oct 23, 2025 by HuiGao-NV • Draft
1 task
3
[https://nvbugs/5597647][fix] Fix MNNVL Allreduce accuracy issue on Hopper
#8612 opened Oct 23, 2025 by timlee0212 Loading…
1 task done
6
[https://nvbugs/5587456][fix] Remove multimodal test cases using TRT backend
#8611 opened Oct 23, 2025 by jieli-matrix Loading…
1 task done
@jieli-matrix
2
[https://nvbugs/5541145][fix] Remove DeepSeekR1 test case from H20 to prevent OOM
#8610 opened Oct 23, 2025 by jieli-matrix Loading…
1 task done
@jieli-matrix
2
[https://nvbugs/5451272][fix] unwaive the test
#8608 opened Oct 23, 2025 by Shixiaowei02 Loading…
5
[None][infra] Minor Update on Perf Sanity Testdb Files
#8607 opened Oct 23, 2025 by chenfeiz0326 Loading…
1 task done
7
[None][test]: Add longbench v2 for long context evaluation
#8604 opened Oct 23, 2025 by baize97 Loading…
1 task
12
[None][fix] Fix e2e tests for phi4mm and NVILA
#8603 opened Oct 23, 2025 by xinhe-nv Loading…
1 task done
1
[TRTLLM-8431][doc] update public doc and example
#8602 opened Oct 23, 2025 by reasonsolo Loading…
1 task done
14
[None] [test] Add MNNVL AlltoAll tests to pre-merge
#8601 opened Oct 23, 2025 by kaiyux Loading…
4
[TRTLLM-8836][chore] Create ModelEngine from LlmArgs
#8600 opened Oct 23, 2025 by QiJune Loading…
1 task done
8
[None][feat] AutoDeploy: Add FP8 MOE for Nemotron
#8599 opened Oct 23, 2025 by nvchenghaoz Loading…
13
[TRTLLM-8511][feat] AutoDeploy: optimize fused_mlp_moe_kernel tiles
#8597 opened Oct 22, 2025 by nzmora-nvidia Loading…
1 task done
8
[AutoDeploy]Add Agent ops
#8594 opened Oct 22, 2025 by suyoggupta • Draft
1 task
ProTip! Exclude everything labeled bug with -label:bug.