-
Notifications
You must be signed in to change notification settings - Fork 351
Pull requests: microsoft/onnxruntime-genai
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix Qwen 3.5 MTP configuration handling
#2547
opened Sep 11, 2026 by
Jiajia Qin (qjia7)
Contributor
Loading…
Add Qwen3.5 Quark GPTQ export support for hybrid attention models
#2545
opened Sep 10, 2026 by
Vishal Jain (VishalX)
Contributor
Loading…
Add INT4 paged KV and DFlash2 builder support
#2544
opened Sep 10, 2026 by
Tianlei Wu (tianleiwu)
Contributor
Loading…
Bump the github-actions group across 1 directory with 16 updates
dependencies
Pull requests that update a dependency file
github_actions
Pull requests that update GitHub Actions code
#2542
opened Sep 9, 2026 by
dependabot
Bot
Loading…
Preserve exact generated prompt length in benchmark
#2541
opened Sep 9, 2026 by
tanzeel-amd
Contributor
Loading…
Implement initial changes for continuous images in multi-modal chat
#2540
opened Sep 8, 2026 by
aciddelgado
Contributor
•
Draft
[WebGPU] Support paged attention models
#2535
opened Sep 4, 2026 by
Tianlei Wu (tianleiwu)
Contributor
Loading…
Fix shared memory race in warp merge sort write-back
#2526
opened Sep 3, 2026 by
Tianlei Wu (tianleiwu)
Contributor
•
Draft
Support multi-image inference for Gemma 4
#2524
opened Sep 2, 2026 by
Akshay Sonawane (apsonawane)
Contributor
Loading…
Fix feature leakage across Qwen multi-image inputs
#2521
opened Sep 2, 2026 by
Akshay Sonawane (apsonawane)
Contributor
Loading…
Support DeepStack (Qwen3-VL) in the vision->embedding->decoder pipeline
#2513
opened Sep 1, 2026 by
Tachion (SanjayAMD)
Contributor
Loading…
feat: accept oci:// model sources in the model builder
#2503
opened Aug 30, 2026 by
Eric Curtin (ericcurtin)
Loading…
1 task done
Generalize Gemma 4 MoE Quark path to plain Quark/AWQ int4 experts
#2483
opened Aug 27, 2026 by
Thiago Pereira Rocha (thpereir)
Contributor
Loading…
3 tasks done
Add 2-bit (uint2) Gemma 4 MoE support to the model builder
#2482
opened Aug 27, 2026 by
Thiago Pereira Rocha (thpereir)
Contributor
Loading…
3 tasks done
[C#] Expose cached Generator through IChatClient.GetService
#2475
opened Aug 27, 2026 by
ZedingZhang (ZedingZhang)
Loading…
Add Gemma 4 text model builder support (dense gemma-4-12b-it + 26B-A4B MoE)
#2473
opened Aug 26, 2026 by
Thiago Pereira Rocha (thpereir)
Contributor
Loading…
Support stateful KV cache for multimodal decoder
#2469
opened Aug 25, 2026 by
Anirudh Swaminathan (Anirudh-Swaminathan)
•
Draft
[benchmark] Add prompt token truncation and trim benchmark output
#2468
opened Aug 25, 2026 by
Namal Rajatheva (amd-namalr)
Loading…
Keep Python opaque data alive for the lifetime of the request
#2445
opened Aug 21, 2026 by
Gopalakrishnan Nallasamy (GopalakrishnanN)
Contributor
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-09-08.