Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
316 Open 2,975 Closed
316 Open 2,975 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

[Infra] - Waive failed cases on recent post-merge
#6212 opened Jul 21, 2025 by EmmaQiaoCh Loading…
2
chore: Mass integration of release/0.21 (part 4)
#6211 opened Jul 21, 2025 by dc3671 Loading…
6
Draft: Deepseek: Start Eagle work
#6210 opened Jul 21, 2025 by IzzyPutterman Loading…
4
bug: [https://nvbugs/5368507] Fix test_generate_with_seed.
#6206 opened Jul 20, 2025 by bobboli Loading…
10
[TRTLLM-6445] feat: Enable AllReduce-associated fusion patterns in Llama3/4.
#6205 opened Jul 20, 2025 by hyukn • Draft
6
Draft: Nanobind integration tests
#6203 opened Jul 20, 2025 by Linda-Stadter • Draft
23
[https://nvbugs/5378031] Hopper W4A8 MoE supports ModelOpt ckpt for PyT backend
#6200 opened Jul 20, 2025 by rosenrodt Loading…
15
Draft: Qwen3: Fix eagle hidden states
#6199 opened Jul 20, 2025 by IzzyPutterman Loading…
2
[https://nvbugs/5361178][fix]: Json schema support in trtllm-serve using xgrammar Community want to contribute PRs initiated from Community
#6197 opened Jul 18, 2025 by mayani-nv Loading…
3
[AutoDeploy] merge feat/ad-2025-07-07
#6196 opened Jul 18, 2025 by lucaslie Loading…
1
@lucaslie
29
fix: Allreduce Strategy is not correctly set for MNNVL fallback.
#6194 opened Jul 18, 2025 by timlee0212 Loading…
@timlee0212
4
DRAFT Changes for multi stream executor
#6190 opened Jul 18, 2025 by nvkgoyal • Draft
1
fix: Ensure that Python stub generation works against libnvidia-ml stubs
#6188 opened Jul 18, 2025 by MartinMarciniszyn Loading…
@MartinMarciniszyn
10
feat: Support Aggregate mode for phi4-mm
#6184 opened Jul 18, 2025 by Wanli-Jiang • Draft
7
[fix] Correct the returned value of has_spec_drafter
#6178 opened Jul 18, 2025 by ziyixiong-nv Loading…
4
[TRTLLM-6357][test] Add accuracy tests for Qwen3
#6177 opened Jul 18, 2025 by reasonsolo Loading…
8
DON'T MERGE: log paused requests info
#6174 opened Jul 18, 2025 by HuiGao-NV • Draft
1
[linting] Enable ruff on more files (wave 2/N)
#6162 opened Jul 17, 2025 by 2ez4bz Loading…
15
[Perf]: Add residual, norm and AR fusions for llama and nemotron_nas models
#6157 opened Jul 17, 2025 by NVShreyas Loading…
24
[feat] Enable TP and batching for PixtralVisionModel / Mistral3VLM
#6152 opened Jul 17, 2025 by 2ez4bz Loading…
25
fix: nanobind build due to undeclared CommType
#6149 opened Jul 17, 2025 by Linda-Stadter Loading…
@Linda-Stadter
12
test: Enable GB200 torch compile multi gpu tests
#6145 opened Jul 17, 2025 by yizhang-nv Loading…
82
[TRTLLM-6537][infra] extend multi-gpu tests related file list
#6139 opened Jul 17, 2025 by reasonsolo Loading…
5
[nvbug/5322354] fix PD + MTP + overlap scheduler accuracy issue
#6136 opened Jul 17, 2025 by yweng0828 Loading…
20
[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure
#6135 opened Jul 17, 2025 by zhengd-nv Loading…
28
ProTip! Adding no:label will show everything without a label.