Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
470 Open 6,915 Closed
470 Open 6,915 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][feat] Expose internal mem pool of KVCacheManagerV2
#11003 opened Jan 26, 2026 by lowsfer Loading…
6
[TRTLLM-9390][chore] Add Fake OPs for One-Sided AlltoAll.
#11002 opened Jan 26, 2026 by bobboli Loading…
1 task
4
[TRTLLM-10382][feat] Support rejection sampling in one-model spec dec
#11001 opened Jan 26, 2026 by ziyixiong-nv Loading…
1 task
6
[https://nvbugs/5779536][fix] Cherry-pick #10902: Unwaive DeepSeekR1 nvfp4 pp4 mtp test case (#10902)
#11000 opened Jan 26, 2026 by pengbowang-nv Loading…
1 task done
4
[TRTLLM-6909][feat] enhance logprobs benchmarking script
#10998 opened Jan 26, 2026 by LinPoly Loading…
1 task
@LinPoly
4
[https://nvbugs/5819452][ci] Unwaive LLaMA2 7B FP8 case
#10997 opened Jan 26, 2026 by syuoni Loading…
1 task done
4
[https://nvbugs/5815025][fix] Fix spec-dec mode flag and related cpp requirements
#10996 opened Jan 26, 2026 by pengbowang-nv Loading…
1 task done
3
[None][feat] Add flux kontext support
#10995 opened Jan 26, 2026 by Wong4j • Draft
1 task done
[None][chore] Add failed cases into waives.txt
#10993 opened Jan 26, 2026 by xinhe-nv • Draft
[None][chore] Add failed cases into waives.txt
#10992 opened Jan 26, 2026 by xinhe-nv • Draft
[None][chore] Add Fake OPs for NVLink OneSided AlltoAll.
#10991 opened Jan 26, 2026 by bobboli Loading…
1 task
3
[None][fix] fix TinyGemm accuracy issue. cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/10619 and https://github.com/NVIDIA/TensorRT-LLM/pull/10873
#10990 opened Jan 26, 2026 by bo-nv Loading…
1 task
@bo-nv
2
[https://nvbugs/5821433][fix] WAR for popen in QA env
#10989 opened Jan 26, 2026 by reasonsolo Loading…
1 task done
4
[TRTLLM-10666][chore] Refactor request fetching logic for better separation of concerns
#10988 opened Jan 26, 2026 by lancelly • Draft
2
[TRTLLM-9831][perf] Use TMA.RED to improve effective memory bandwidth
#10987 opened Jan 26, 2026 by sherry-1001 Loading…
1 task done
8
[https://nvbugs/5756804][fix] Re-enable passing test
#10986 opened Jan 26, 2026 by dongfengy Loading…
1 task done
4
[TRTLLM-10064][feat] MoE all-to-all paradigm
#10985 opened Jan 25, 2026 by greg-kwasniewski1 Loading…
1 task done
1
21
[None][chore] Remove closed bugs
#10982 opened Jan 25, 2026 by xinhe-nv Loading…
4
[None][chore] update AD model list
#10981 opened Jan 25, 2026 by tcherckez-nvidia Loading…
1 task done
4
[None][infrea] cherry pick lock file fix to release/1.2
#10975 opened Jan 25, 2026 by yuanjingx87 Loading…
1 task done
3
[None][chore] Add failed cases into waives.txt
#10973 opened Jan 24, 2026 by xinhe-nv • Draft
[#9460][feat] AutoDeploy: Fully-fledged GPT-OSS support
#10968 opened Jan 24, 2026 by Fridah-nv • Draft
2 of 4 tasks
@Fridah-nv
1
[https://nvbugs/5835925][fix] Add EPD disagg support for Qwen3 VL MoE
#10962 opened Jan 23, 2026 by 2ez4bz Loading…
1 task done
4
[None][infra] Add source code pulse scan to PLC nightly pipeline
#10961 opened Jan 23, 2026 by yuanjingx87 Loading…
1 task done
6
[TRTLLM-10197][chore] Refactor to setup for RNN cache transceiver
#10957 opened Jan 23, 2026 by NVShreyas Loading…
1 task done
20
ProTip! Follow long discussions with comments:>50.