Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
397 Open 4,039 Closed
397 Open 4,039 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] Bump version to 1.1.0rc4
#7525 opened Sep 4, 2025 by yiqingy0 Loading…
1 task
1
[None][chore] Change moe backend in DeepSeek-R1 fp8 test to TRTLLM
#7524 opened Sep 4, 2025 by pengbowang-nv • Draft
1 task
1
[None][chore] Upgrade transformers to 4.56.0
#7523 opened Sep 4, 2025 by Wanli-Jiang • Draft
1 task done
2
fix: convert_load_format for int and str enum
#7522 opened Sep 4, 2025 by weedge Loading…
1 task
3
[TRTLLM-6308][feat] Support Aggregate mode for phi4-mm
#7521 opened Sep 4, 2025 by Wanli-Jiang Loading…
1 task done
8
[TRTLLM-7349][feat] Adding new Ray orchestrator
#7520 opened Sep 4, 2025 by joyang-nv Loading…
1 task
100
[None][chore] Mass integration of release/1.0 - 3rd
#7519 opened Sep 4, 2025 by dominicshanshan Loading…
1 task done
18
[TRTLLM-7292][feat] Disable gc in trtllm serve
#7518 opened Sep 4, 2025 by nv-yilinf • Draft
1 task
[TRTLLM-6496][feat] Add LoRa Torch tests for the latest NIM model list - TEMP DRAFT to run tests on 8xH200
#7517 opened Sep 4, 2025 by moraxu • Draft
1 task
2
[None][chore] remove executor config in instantiate sampler
#7516 opened Sep 4, 2025 by leslie-fang25 • Draft
1 task done
2
[TRTLLM-7292][feat] Support multi-threaded tokenizers for trtllm-serve
#7515 opened Sep 4, 2025 by nv-yilinf Loading…
1 task done
5
[TRTLLM-6589][feat] Support CUDA graph for DeepEP
#7514 opened Sep 4, 2025 by yifeizhang-c • Draft
1
[https://nvbugs/5474409][fix] Potential fix for oom
#7512 opened Sep 3, 2025 by arekay Loading…
1 task
4
[None][fix] Assign [] to req.py_draft_tokens instead of None when spec decode is OFF. Also fix dynamic spec decode unit test.
#7511 opened Sep 3, 2025 by zheyuf Loading…
1 task
2
[TRTLLM-6371][feat] Restructure C++ KVCacheManager to better handle limited attention layers
#7510 opened Sep 3, 2025 by thorjohnsen • Draft
1 task
[https://nvbugs/5496960][fix] Fix Gemma model forward.
#7509 opened Sep 3, 2025 by hyukn Loading…
5
[TRTLLM-7779][feat] Support multiple postprocess workers for chat completions API
#7508 opened Sep 3, 2025 by JunyiXu-nv Loading…
1 task done
25
[https://nvbugs/5494698][fix] skip gemma3 27b on blackwell
#7505 opened Sep 3, 2025 by xinhe-nv Loading…
1 task
2
[None][ci] restructure llmapi related test lists
#7504 opened Sep 3, 2025 by Superjomn Loading…
1 task done
6
[TRTLLM-7871][infra] (DO NOT REVIEW) initial changes
#7503 opened Sep 3, 2025 by bo-nv Loading…
1 task
9
[TRTLLM-7854][infra] Add gemm test before pytest stage to check machine status
#7500 opened Sep 3, 2025 by yiqingy0 • Draft
1 task
14
[TRTLLM-7318][feat]New MoE AlltoAll implementation.
#7499 opened Sep 3, 2025 by bobboli • Draft
1 task
31
[https://nvbugs/5351244][fix] test_mpi_session
#7498 opened Sep 3, 2025 by Superjomn Loading…
1 task done
5
[TRTLLM-7351][infra] Add isolate marker for L0
#7497 opened Sep 3, 2025 by EmmaQiaoCh Loading…
1 task done
17
feat: add model seed-oss Community want to contribute PRs initiated from Community
#7496 opened Sep 3, 2025 by Nekofish-L Loading…
1 task done
7
ProTip! Mix and match filters to narrow down what you’re looking for.