Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
52 Open 1,533 Closed
52 Open 1,533 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

fix(ci): use new github-ci identity for docker pull
#2263 opened Jul 3, 2026 by sanaa-hamel-microsoft Contributor Loading…
1
Moonshine Model Streaming Test Development
#2262 opened Jul 3, 2026 by themason2011 Loading…
Avoid disclosing config file contents in parse error messages
#2261 opened Jul 2, 2026 by jiafatom Contributor Loading…
2
Add bounds checking to OgaSequencesGetSequence C API functions
#2260 opened Jul 2, 2026 by jiafatom Contributor Loading…
4
Add GetMemoryInfo to DeviceInterface
#2259 opened Jul 2, 2026 by qti-mattsinc Contributor Loading…
4
Update trust_remote_code
#2256 opened Jul 2, 2026 by apsonawane Contributor Loading…
4
Resolve model package paths and path-valued session options through ONNX Runtime
#2255 opened Jul 2, 2026 by jambayk Contributor • Draft
4
chore(ci): use new integration test pool on Linux
#2254 opened Jul 2, 2026 by sanaa-hamel-microsoft Contributor Loading…
1
Generate pyd type info
#2247 opened Jun 29, 2026 by themason2011 Loading…
7
webgpu: bypass manual mRoPE for text-only Qwen3.5 when GQA fuses RoPE
#2245 opened Jun 26, 2026 by qjia7 Contributor • Draft
3 tasks
2
webgpu: fix RecurrentState graph capture with shared buffer aliasing
#2244 opened Jun 26, 2026 by qjia7 Contributor Loading…
5 tasks done
6
Implement no_repeat_ngram_size for CPU search
#2242 opened Jun 25, 2026 by mustjab Loading…
5
[Doc] Cuda Plugin EP integration
#2236 opened Jun 22, 2026 by tianleiwu Contributor • Draft
10
Add StaticScatterKeyValueCache: drive mobius bias-aware external-KV (TensorScatter + nonpad_kv_seqlen) static cache
#2235 opened Jun 20, 2026 by titaiwangms Contributor Loading…
1
10
Update model builder for gpt-oss
#2234 opened Jun 19, 2026 by tianleiwu Contributor • Draft
3 of 4 tasks
46
Add speculative decoding implementation (draft + target verification) (v0)
#2233 opened Jun 19, 2026 by samsat701 Loading…
33
Add option of fp4 QMoE for gpt-oss in model builder
#2229 opened Jun 15, 2026 by tianleiwu Contributor • Draft
5
Add address validation feature
#2223 opened Jun 11, 2026 by apsonawane Contributor Loading…
7
Add path traversal validation
#2222 opened Jun 11, 2026 by apsonawane Contributor Loading…
4
Qwen3.6 MTP
#2218 opened Jun 11, 2026 by tianleiwu Contributor • Draft
5
Add Tool Calling and Reasoning Token Metadata to genai_config.json with Fallback Map
#2215 opened Jun 11, 2026 by sayanshaw24 Collaborator Loading…
7
Bump torch from 2.7.1+cpu to 2.12.0+cpu in /test/python/cpu/torch dependencies Pull requests that update a dependency file python Pull requests that update python code
#2213 opened Jun 11, 2026 by dependabot Bot Loading…
1
Bump torch from 2.7.1 to 2.12.0+cpu in /test/python/macos/torch dependencies Pull requests that update a dependency file python Pull requests that update python code
#2212 opened Jun 11, 2026 by dependabot Bot Loading…
1
[feat]: support qwen3 prompt embeds
#2211 opened Jun 10, 2026 by huisunCompiler Loading…
6
Pipeline-as-Config: structural model dispatch (#2114)
#2210 opened Jun 10, 2026 by justinchuby Contributor • Draft
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.