Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
40 Open 1,462 Closed
40 Open 1,462 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

Auto-detect fixed kv-cache shape in DefaultKeyValueCache 0.14.0
#2166 opened May 18, 2026 by akholodnamdcom Contributor Loading…
8
Add MIGraphX execution provider support
#2165 opened May 14, 2026 by aditya-dl Loading…
25
Add text-only mode support for Qwen 3.5 model builder 0.14.0
#2157 opened May 12, 2026 by apsonawane Contributor Loading…
20
Add per-run profiling config for fine-grained Run() profiling
#2152 opened May 9, 2026 by xiaofeihan1 Contributor • Draft
Add gemma4 unit tests
#2151 opened May 8, 2026 by apsonawane Contributor Loading…
7
Nvidia Parakeet Tdt ASR support 0.14.0
#2150 opened May 8, 2026 by nenad1002 Contributor Loading…
41
Add VideoChat-Flash (OpenGVLab) language model support 0.14.0
#2147 opened May 8, 2026 by anilmartha Contributor Loading…
4 tasks
16
Add Qwen3.5-MoE (35B-A3B) model support 0.14.0
#2146 opened May 8, 2026 by tanzeel-amd Loading…
8
Expose mutable sampling parameters on live Generator
#2145 opened May 8, 2026 by qjia7 Contributor Loading…
4 tasks done
4
Add HunYuan Dense V1 (hunyuan_v1_dense) model support 0.14.0
#2144 opened May 8, 2026 by anilmartha Contributor Loading…
12
fix: enable Generator.rewind_to(0) for multimodal models
#2141 opened May 8, 2026 by justinchuby Contributor • Draft
1
12
Enable Qwen3.5 TRT-RTX EP path with CUDA graph 0.14.0
#2139 opened May 7, 2026 by yen-shi Loading…
36
Supply JobId to runs-on
#2138 opened May 7, 2026 by baijumeswani Collaborator Loading…
3
[Qwen3] Allow packed QKV MatMul under QK-Norm via post-MatMul Split 0.14.0
#2137 opened May 7, 2026 by xiaofeihan1 Contributor Loading…
7
model package integration
#2136 opened May 6, 2026 by xiaoyu-work Contributor Loading…
5
Fix Gemma4 pixel_values trimming
#2135 opened May 6, 2026 by apsonawane Contributor Loading…
4
Cohere Transcribe Support
#2133 opened May 6, 2026 by nenad1002 Contributor Loading…
16
Add granitemode support 0.14.0
#2124 opened May 6, 2026 by amdrajeevp1 Contributor Loading…
4 tasks
3
Fix multimodal CUDA pipeline: embedding output persistence causes shape mismatch
#2123 opened May 5, 2026 by justinchuby Contributor Loading…
1
13
Add Seed-OSS architecture support (SeedOssForCausalLM)
#2116 opened May 3, 2026 by PMeeske Loading…
12
Pipeline-as-Config: Declarative model dispatch replacing model_type string registry
#2115 opened May 2, 2026 by justinchuby Contributor • Draft
1
8
Fix AppendNextTokensToSequences heap overflow
#2111 opened Apr 30, 2026 by apsonawane Contributor Loading…
4
Fix heap overflow issue
#2110 opened Apr 30, 2026 by apsonawane Contributor Loading…
6
Add linux-aarch64 support 0.14.0
#2107 opened Apr 29, 2026 by baijumeswani Collaborator • Draft
Release captured graph resources when generator is destroyed
#2106 opened Apr 29, 2026 by qjia7 Contributor • Draft
ProTip! Updated in the last three days: updated:>2026-05-16.