Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
485 Open 6,186 Closed
485 Open 6,186 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

draft for prealloc cpp kvcache transceiver
#10153 opened Dec 19, 2025 by reasonsolo • Draft
1 task
[https://nvbugs/5752516][chore] unwaive test; move some test_auto_scaling tests from L0 to qa test list
#10152 opened Dec 19, 2025 by reasonsolo Loading…
1 task done
5
[None][infra] Update waive and waive failed tests for main branch on 12/19
#10151 opened Dec 19, 2025 by EmmaQiaoCh Loading…
1 task done
8
[#8460][feat] Revive and simplify Model Explorer visualization integration
#10150 opened Dec 19, 2025 by karthikvetrivel Loading…
1 task done
1
5
[TRTLLM-9880][feat] Include torch compile tests in QA test list
#10149 opened Dec 19, 2025 by liji-nv Loading…
1 task done
3
[None][fix] NVFP4 linear method's weight and weight_scale padding
#10148 opened Dec 19, 2025 by JadoTu Loading…
1 task done
9
[https://nvbugs/5702793][fix] Fix view operation on uncontiguous tensor
#10147 opened Dec 19, 2025 by shuyixiong Loading…
1 task done
@shuyixiong
3
[TRTLLM-9896][test] add vswa test cases coverage
#10146 opened Dec 19, 2025 by crazydemo Loading…
1 task done
1
Mistral large 3 VLM updates + SLMs
#10142 opened Dec 19, 2025 by evezhier Loading…
1 task
[None][feat] Cudagraph updates for helix parallelism
#10141 opened Dec 18, 2025 by brb-nv Loading…
1 task done
16
[https://nvbugs/5748564][fix] Unwaiving auto_scaling disagg test
#10140 opened Dec 18, 2025 by pcastonguay Loading…
1 task done
3
[#10137][feat] AutoDeploy FP8 MoE refactor
#10138 opened Dec 18, 2025 by nzmora-nvidia Loading…
1 task
4
[https://nvbugs/5747674][fix] Add contiguous() before view() in load_expert_w3_w1_weight and load
#10136 opened Dec 18, 2025 by farazkh80 Loading…
1 task done
6
[TRTLLM-8638][fix] Add failed cases into waives.txt
#10132 opened Dec 18, 2025 by xinhe-nv Loading…
3
[#10056][test] AutoDeploy: Add accuracy test for Nemotron SuperV3
#10131 opened Dec 18, 2025 by galagam Loading…
11
[TRTLLM-9457] Add cute dsl fp8 gemm for Blackwell
#10130 opened Dec 18, 2025 by yifeizhang-c • Draft
1 task
[TRTLLM-8638][fix] Add failed cases into waives.txt
#10129 opened Dec 18, 2025 by xinhe-nv Loading…
3
[TRTC-119][feat] BREAKING: LLMAPI auto-fallback for unsupported features
#10127 opened Dec 18, 2025 by venkywonka • Draft
1 task
1
[TRTLLM-9677][feat] Support DeepSeek-V3.2 tool parser
#10126 opened Dec 18, 2025 by lfr-0531 • Draft
1 task
[TRTC-121] [feat] Add recipe selector UI to complement the recipe database
#10125 opened Dec 18, 2025 by venkywonka • Draft
1 task
@venkywonka
4
[TRTC-122][bug] Fix eagle3 draft vocab fallback
#10124 opened Dec 18, 2025 by venkywonka • Draft
1 task
5
[https://nvbugs/5747930][fix] Use offline tokenizer for whisper models.
#10121 opened Dec 18, 2025 by yuxianq Loading…
1 task done
5
[None][fix] avoid implicit cudaStreamSynchronize in sample_async.
#10120 opened Dec 18, 2025 by yuxianq Loading…
1 task done
4
[None][feat] Support multi-gpu running for nemotron-v3-nano
#10118 opened Dec 18, 2025 by Wanli-Jiang Loading…
1 task done
4
[None][feat] Export ONNX for DriveOS LLM Community want to contribute PRs initiated from Community
#10117 opened Dec 18, 2025 by nvyocox • Draft
1 task
26
ProTip! What’s not been updated in a month: updated:<2025-11-18.