Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
430 Open 5,052 Closed
430 Open 5,052 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

test ci models
#8731 opened Oct 28, 2025 by HuiGao-NV Loading…
1 task
5
[None][fix] fix config loading for DeepSeek-V3.2 in trtllm-bench
#8729 opened Oct 28, 2025 by lfr-0531 Loading…
1 task done
7
[feat][None] Integrate MnnvlThroughput into TRTLLM MoE.
#8728 opened Oct 28, 2025 by bobboli • Draft
1 task
[https://nvbugs/5422621][fix] fix EPLB init hang (cherry-pick #8649)
#8727 opened Oct 28, 2025 by syuoni Loading…
1 task done
3
[None][test] fix a typo in perf test sampler config
#8726 opened Oct 28, 2025 by ruodil Loading…
1 task done
7
[TRTLLM-8971][infra] Update gpu key for B300/GB300
#8724 opened Oct 28, 2025 by EmmaQiaoCh Loading…
1 task done
4
[https://nvbugs/5613089][fix] Fix the rank to access all_rank_chunk_size_list when chunked MoE is used
#8723 opened Oct 28, 2025 by jinyangyuan-nvidia Loading…
1 task done
4
MXFP4 x BF16 CUTLASS MoE backend perf and profiling improvement on Hopper
#8721 opened Oct 28, 2025 by StudyingShao Loading…
1 task
7
[None][fix] Enable GDRCopy and unwaive online eplb tests
#8720 opened Oct 28, 2025 by dongxuy04 • Draft
1 task done
2
[None][fix] fix dockerfile: resolve installation issue caused by setup.py Community want to contribute PRs initiated from Community
#8719 opened Oct 28, 2025 by lkm2835 Loading…
1 task done
1
[None][feat] Add unit tests and revision in block_level kernel for invalid input
#8718 opened Oct 28, 2025 by ChristinaZ Loading…
1 task done
8
[TRTLLM-8763][chore] Deprecate pybind based GuidedDecodingConfig usage in torch backend
#8717 opened Oct 28, 2025 by leslie-fang25 • Draft
1 task done
2
[None][chore] Add unittest for otlp tracing Community want to contribute PRs initiated from Community
#8716 opened Oct 28, 2025 by zhanghaotong Loading…
1 task done
6
[TRTLLM-8920][feat] decouple disagg service from fastapi
#8714 opened Oct 28, 2025 by reasonsolo • Draft
1 task
[None][chore] Enable GPQA in CI for DeepSeek V3.2
#8712 opened Oct 28, 2025 by chang-l Loading…
1 task done
6
[None][fix] RPC stability
#8711 opened Oct 28, 2025 by Superjomn Loading…
1 task
4
[https://nvbugs/5612529][fix] Fix transferAgent_test
#8710 opened Oct 28, 2025 by chuangz0 Loading…
1 task done
4
[https://nvbugs/5325296][fix] Enable relaxed acceptance test on Blackwell
#8709 opened Oct 28, 2025 by Barry-Delaney Loading…
@Barry-Delaney
6
[https://nvbugs/5550409][fix]Disable torch compile in piecewise attention part to Avoid host overhead
#8708 opened Oct 28, 2025 by yizhang-nv Loading…
1 task
8
[https://nvbugs/5599086][fix] Fix FP8 Linear module for spark
#8707 opened Oct 28, 2025 by SimengLiu-nv Loading…
1 task done
5
[TRTLLM-8084][feat] Enhance the overlap shceduler for two-model spec decoding
#8706 opened Oct 28, 2025 by ziyixiong-nv • Draft
1 task
1
[None][fix] InputProcessor config naming convention fix Multimodal Label for issues & PRs regarding Multimodal related objects
#8705 opened Oct 28, 2025 by yechank-nvidia Loading…
@yechank-nvidia
8
[https://nvbugs/5608461][fix] exclude InductorSubproc from thread leak check
#8704 opened Oct 28, 2025 by leslie-fang25 Loading…
1 task done
9
[TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 2).
#8703 opened Oct 28, 2025 by zheyuf • Draft
1 task
[https://nvbugs/5596343][test] Update test waive to get back some coverage
#8702 opened Oct 27, 2025 by dongfengy Loading…
1 task done
4
ProTip! Follow long discussions with comments:>50.