Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
483 Open 6,282 Closed
483 Open 6,282 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

[TRTLLM-10143][feat] Reuse previous draft requests if possible
#10263 opened Dec 24, 2025 by ziyixiong-nv Loading…
1 task
[None][test] Add disag-serving auto scaling qa test
#10262 opened Dec 24, 2025 by StanleySun639 Loading…
1 task done
2
[None][feat] update trtllm-gen to support groupsTokensHeadsQ
#10261 opened Dec 24, 2025 by PerkzZheng • Draft
1 task done
7
[https://nvbugs/5740359][chore] Unwaive tests.
#10260 opened Dec 24, 2025 by yuxianq Loading…
1 task done
6
[https://nvbugs//5584607][fix] Ray supports nixl backend
#10259 opened Dec 24, 2025 by chuangz0 Loading…
1 task done
3
[None][feat] Drop non-deepgemm fp8 block scale gemm
#10256 opened Dec 24, 2025 by lucifer1004 Loading…
1 task done
8
[TRTLLM-10016][infra] Use SlurmPatition attribute time as timeout threshold
#10254 opened Dec 24, 2025 by yiqingy0 • Draft
1 task
2
[None][infra] Check GB200 coherent GPU mapping
#10253 opened Dec 24, 2025 by yiqingy0 • Draft
1 task
6
[#10244][feat] AutoDeploy: separate prefill/decode in flashinfer
#10252 opened Dec 24, 2025 by lucaslie Loading…
1 task done
1
12
[None][feat] Not CUDA graph captured eagle3 one-model draft loop
#10251 opened Dec 24, 2025 by jhaotingc Loading…
1 task done
8
[None][chore] Upgrade transformers to 4.57.3
#10250 opened Dec 24, 2025 by nv-guomingz Loading…
1 task done
4
[None][chore] Add failed cases into waives.txt
#10249 opened Dec 24, 2025 by xinhe-nv • Draft
[None][chore] Update tinygemm kernel name
#10248 opened Dec 24, 2025 by longlee0622 Loading…
1 task done
7
[#8391][chore] added llama_v3.3_70b_instruct AutoDeploy perf test to L0
#10242 opened Dec 23, 2025 by MrGeva Loading…
1 task done
@MrGeva
6
[None][chore] Add failed cases into waives.txt
#10240 opened Dec 23, 2025 by xinhe-nv Loading…
10
[None][chore] Unify DS tool parser names
#10239 opened Dec 23, 2025 by LinPoly Loading…
1 task done
@LinPoly
3
[None][feat] Add gpt_oss_120b to layer_wise_benchmarks
#10238 opened Dec 23, 2025 by WeiHaocheng • Draft
1 task
[None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts
#10237 opened Dec 23, 2025 by yuantailing Loading…
1 task done
13
[None][chore] refine placement group in ray executor
#10235 opened Dec 23, 2025 by Superjomn Loading…
1 task
3
[TRTLLM-10065][feat] Add accuracy tests for nano-v3 and super-v3 with multiple-gpus
#10234 opened Dec 23, 2025 by Wanli-Jiang • Draft
1 task
[None][chore] Remove NIM TRT-Backend Test Lists
#10232 opened Dec 23, 2025 by jieli-matrix Loading…
1 task done
@jieli-matrix
8
[https://nvbugs/5747938][fix] Use local tokenizer
#10230 opened Dec 23, 2025 by LinPoly Loading…
1 task done
@LinPoly
9
[TRTLLM-10126][feat] Increase topk upper limit to 22 for NVLinkOneSid…
#10229 opened Dec 23, 2025 by nv-guomingz Loading…
1 task done
12
[TRTLLM-8577][feat] Clean the Qwen3-next code by removing Qwen3NextCo…
#10228 opened Dec 23, 2025 by nv-guomingz Loading…
1 of 2 tasks
11
[https://nvbugs/5752521][fix] Unwaive test_trtllm_flashinfer_symbol_collision.py
#10227 opened Dec 23, 2025 by yihwang-nv Loading…
9
ProTip! Add no:assignee to see everything that’s not assigned.