Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
481 Open 6,546 Closed
481 Open 6,546 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] Fix Gitlab CI termination issues
#10576 opened Jan 9, 2026 by fredricz-20070104 Loading…
[None][chore] Add test configurable moe module
#10575 opened Jan 9, 2026 by leslie-fang25 • Draft
1 task done
[TRTLLM-10155][infra] Update trtllm-release image stage to tritonrelease, and make this build from source, not devel
#10574 opened Jan 9, 2026 by ZhanruiSunCh • Draft
1 task
[None][infra] Empty PR for testing bot
#10573 opened Jan 9, 2026 by mzweilz Loading…
1 task
6
[None][test] Remove most TRT-backend test cases in llm_perf_nim.yml
#10572 opened Jan 9, 2026 by yufeiwu-nv Loading…
1 task done
4
[TRTLLM-10309] [feat] Optimize qk rope/nope concat for DSA
#10571 opened Jan 9, 2026 by kaiyux Loading…
1 task
7
[https://nvbugs/5707359][fix] Unwaive the test that due to flashinfer…
#10570 opened Jan 9, 2026 by liji-nv Loading…
1 task done
3
[https://nvbugs/5787566][fix] Only keep a limited number of performance statistic records
#10569 opened Jan 9, 2026 by HuiGao-NV Loading…
1 task done
4
[None][doc] blog: Optimizing DeepSeek-V3.2 on NVIDIA Blackwell GPUs
#10565 opened Jan 9, 2026 by lfr-0531 Loading…
1 task done
9
[TRTLLM-10271][test] Add Spark QA functional and performance cases
#10564 opened Jan 9, 2026 by JennyLiu-nv Loading…
1 task done
5
[None][chore] remove some model support; add device constraint
#10563 opened Jan 9, 2026 by jieli-matrix Loading…
1 task done
@jieli-matrix
6
[None][feat] Layer-wise benchmarks: make model init more general and support weights loading
#10562 opened Jan 9, 2026 by yuantailing Loading…
1 task
11
[None][feat] Add support for DeepSeek v3.2 tests
#10561 opened Jan 9, 2026 by yingguo-trt Loading…
1 task done
10
[https://nvbugs/5598674][fix] enable partial reuse in gemma and gpt oss test
#10559 opened Jan 9, 2026 by chuangz0 Loading…
1 task done
4
[None][chore] TEST non_mix_batching scheduler with overlap scheduler
#10558 opened Jan 9, 2026 by lancelly • Draft
[None][fix] Experiment of allreduce tuning time after pruning.
#10557 opened Jan 9, 2026 by hyukn • Draft
1 task
2
[None][chore] Add failed cases into waives.txt
#10554 opened Jan 8, 2026 by xinhe-nv • Draft
[https://nvbugs/5752687][fix] Choose register model config over root config for VLM Multimodal Label for issues & PRs regarding Multimodal related objects
#10553 opened Jan 8, 2026 by farazkh80 Loading…
1 task done
9
[None][fix] Fix vulnerabilities of gpg and nbconvert
#10551 opened Jan 8, 2026 by yiqingy0 • Draft
1 task
3
Remove pybind
#10550 opened Jan 8, 2026 by Linda-Stadter • Draft
1 task
6
[https://nvbugs/5664908][fix] Unwaive test
#10544 opened Jan 8, 2026 by dominicshanshan Loading…
1 task done
9
[TRTLLM-10273][feat] Move MambaCacheManager from Python to C++
#10540 opened Jan 8, 2026 by Tabrizian Loading…
1 task done
3
[TRTLLM-10296][fix] Fix the potential misaligned access due to vectorized ld/st instructions in NVLinkOneSided A2A.
#10539 opened Jan 8, 2026 by bobboli Loading…
1 task
15
[None][test] update core test list
#10538 opened Jan 8, 2026 by crazydemo Loading…
1 task done
10
[None][fix] Solve pillow version conflict Multimodal Label for issues & PRs regarding Multimodal related objects
#10537 opened Jan 8, 2026 by Wanli-Jiang Loading…
1 task done
9
ProTip! Filter pull requests by the default branch with base:main.