Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
372 Open 3,232 Closed
372 Open 3,232 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-5563][infra] Move test_rerun.py to script folder
#6571 opened Aug 2, 2025 by yiqingy0 Loading…
2
[None][fix] Fix attention dp log
#6570 opened Aug 2, 2025 by Shunkangz Loading…
4
[None][feat] Add GPTQ Int8 Options for Qwen TRT path
#6568 opened Aug 1, 2025 by JyChang012 Loading…
1
[TRTLLM-6090] doc: Add multimodal part to the feature section
#6567 opened Aug 1, 2025 by chang-l Loading…
1
[None][doc] Add new doc Community want to contribute PRs initiated from Community
#6565 opened Aug 1, 2025 by jamieliNVIDIA Loading…
4
[TRTLLM-5500][infra] Update CODEOWNERS with new ownership rules for additional paths
#6564 opened Aug 1, 2025 by venkywonka • Draft
@venkywonka
5
Draft: feat: Include attention dp rank info with KV cache events
#6563 opened Aug 1, 2025 by pcastonguay Loading…
7
[TRTLLM-6069]doc: add trtllm-serve usage for cli reference section
#6562 opened Aug 1, 2025 by nv-guomingz Loading…
1
draft: measure the first two tokens interval
#6561 opened Aug 1, 2025 by Shixiaowei02 Loading…
3
[None][chore] Add unit test for Gemma3 lora
#6560 opened Aug 1, 2025 by brb-nv Loading…
8
[None][refactor] Simplify decoder request initialization
#6559 opened Aug 1, 2025 by Funatiq • Draft
7
[None][feat]Support to share device buffers in attention meta
#6557 opened Aug 1, 2025 by HuiGao-NV • Draft
15
[None][infra] fix Build Docker Image tag issue
#6555 opened Aug 1, 2025 by ZhanruiSunCh Loading…
6
[https://nvbugs/5252313][fix] Fix torch compile + MTP
#6554 opened Aug 1, 2025 by liji-nv Loading…
4
[None][doc] Create deployment guide for Llama4 Scout FP8 and NVFP4
#6550 opened Aug 1, 2025 by chenfeiz0326 Loading…
8
[None][feat] improve dataloading for benchmark_dataset by using batch…
#6548 opened Aug 1, 2025 by zerollzeng Loading…
7
feat: Support custom repo_dir for SLURM script
#6546 opened Aug 1, 2025 by kaiyux Loading…
7
[TRTLLM-4501][feat] AutoTuner tuning config refactor and add tuning for kernel configs.
#6545 opened Aug 1, 2025 by hyukn Loading…
6
[None][chore] Mass integration of release/0.21 (part5)
#6544 opened Aug 1, 2025 by dc3671 Loading…
11
[None][doc] Create deployment guide for Llama 3.3 70B FP8 and NVFP4 Community want to contribute PRs initiated from Community
#6543 opened Aug 1, 2025 by jamieliNVIDIA Loading…
13
Speculative Rejection Sampler for 2 model
#6542 opened Aug 1, 2025 by IzzyPutterman Loading…
7
[None][fix] Fix NCCL Ops when using MoE chunking
#6541 opened Aug 1, 2025 by jinyangyuan-nvidia • Draft
1
[TRTLLM-6263][feat] Enable fp8 SwiGLU to minimize host overhead
#6540 opened Aug 1, 2025 by JunyiXu-nv Loading…
10
[None][feat] Use Separate QKV Input Layout for Context MLA
#6538 opened Aug 1, 2025 by zhhuang-nv Loading…
16
[https://nvbugs/5394392] [Fix] Enlarge scheduler and slot manager capacity under disagg bs == 1
#6537 opened Aug 1, 2025 by yifeizhang-c Loading…
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.