Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
379 Open 3,932 Closed
379 Open 3,932 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

[https://nvbugs/5445466][fix] Eliminate race when loading HF dynamic modules (#7268)
#7379 opened Aug 29, 2025 by chang-l Loading…
1 task
5
[None][Doc] Polish parallelism doc and add wide ep sectionwq. 1.0_doc
#7378 opened Aug 29, 2025 by nv-guomingz Loading…
1 task
1
[TRTLLM-7008][fix] Add automatic shared memory delete if already exist
#7377 opened Aug 29, 2025 by dongxuy04 Loading…
1 task done
10
[None][feat] wide_ep support block-wise FP8 on blackwell
#7376 opened Aug 29, 2025 by xxi-nv Loading…
1 task done
6
[None] [fix] store blog 10 media via lfs
#7375 opened Aug 29, 2025 by Funatiq Loading…
1 task done
5
[https://nvbugs/5485325][fix] Add a postprocess to the model engine to fix the CUDA graph warmup issue when using speculative decoding
#7373 opened Aug 29, 2025 by lfr-0531 Loading…
1 task done
7
[None][chore] rm executor config in kv cache connector
#7372 opened Aug 29, 2025 by leslie-fang25 Loading…
1 task done
14
[TRTLLM-7261][feat] Support phi-4 model in pytorch backend
#7371 opened Aug 29, 2025 by Wanli-Jiang • Draft
1 task
[TRTLLM-6747][feat] Merge add sparse exp and shared exp into local reduction
#7369 opened Aug 29, 2025 by zongfeijing Loading…
1 task
14
[https://nvbugs/5485593][fix] improve accuracy/test_disaggregated_serving.py
#7366 opened Aug 29, 2025 by reasonsolo Loading…
1 task
4
[TRTLLM-7279][test] add accuracy test for deepseek-r1 with chunked_prefill
#7365 opened Aug 29, 2025 by crazydemo Loading…
1 task done
3
[TRTLLM-7330][feat]Eagle3 cuda graph support for the 1st draft model inference Community want to contribute PRs initiated from Community
#7363 opened Aug 29, 2025 by sunnyqgg Loading…
1 task
13
[TRTLLM-6642][feat] add gptoss 20g tests
#7361 opened Aug 29, 2025 by xinhe-nv • Draft
1 task
1
[TRTLLM-7410][feat] Enable video modality for hashing/kv_reuse and generalize finding mm_token_length
#7360 opened Aug 29, 2025 by chang-l Loading…
1 task
5
[None] [doc] Update DeepSeek example doc
#7358 opened Aug 29, 2025 by jiahanc Loading…
1 task
9
[None][fix] Revert TP Sharding read from the model config (#6972) bug Something isn't working
#7356 opened Aug 29, 2025 by lucaslie Loading…
1 task done
@lucaslie
8
[None][feat] Support DeepGEMM swap-AB on sm100
#7355 opened Aug 29, 2025 by Barry-Delaney • Draft
@Barry-Delaney
7
Perf/gpt oss eagle
#7353 opened Aug 28, 2025 by ameynaik-hub Loading…
6
[None][chore] Fix formatting error in Gemma3 readme
#7352 opened Aug 28, 2025 by karljang Loading…
1 task done
7
[TRTLLM-5059][feat] Add kv cache reuse for LlavaNext
#7349 opened Aug 28, 2025 by chang-l Loading…
1 task
7
[None][fix] Fix KV cache recompute in draft_target spec decode
#7348 opened Aug 28, 2025 by mikeiovine Loading…
1 task done
5
[None][doc] Update doc for multimodal
#7347 opened Aug 28, 2025 by chang-l Loading…
1 task
3
draft: enable LM tp for MTP, under attention dp case
#7344 opened Aug 28, 2025 by dongxuy04 • Draft
1 task
8
[None][chore] Add env var to disable harmony
#7343 opened Aug 28, 2025 by LinPoly Loading…
1 task done
3
[TRTLLM-7250][fix] Add failed cases into waives.txt
#7342 opened Aug 28, 2025 by xinhe-nv Loading…
9
ProTip! Type g i on any issue or pull request to go back to the issue listing page.