pFad - Phone/Frame/Anonymizer/Declutterfier! Saves Data!


--- a PPN by Garber Painting Akron. With Image Size Reduction included!

URL: http://github.com/microsoft/onnxruntime-genai/pulls

https://github.githubassets.com/assets/github-cf976967feea1e66.css" /> Pull requests · microsoft/onnxruntime-genai · GitHub
Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
39 Open 1,606 Closed
39 Open 1,606 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

Support Quantized KV Cache
#2321 opened Jul 24, 2026 by tianleiwu Contributor Loading…
23
test: cover DML graph capture opt-out
#2316 opened Jul 22, 2026 by gianlucamazza Contributor • Draft
1
Update n-gram speculative decoding implementation (v1)
#2315 opened Jul 21, 2026 by samsat701 • Draft
Add n-gram speculative decoding implementation (v0)
#2314 opened Jul 21, 2026 by samsat701 Loading…
Add Python telemetry for model builder and benchmarks
#2309 opened Jul 20, 2026 by bmehta001 Contributor Loading…
@bmehta001
274
for vlm model, add AppendInputs for multi-turn chat
#2308 opened Jul 20, 2026 by lishixlnx Loading…
5
Add Moonshine streaming ASR model support
#2302 opened Jul 17, 2026 by nenad1002 Contributor Loading…
4
Add Nemotron Parse support
#2301 opened Jul 16, 2026 by ttyio Loading…
25
docs: unified model builder quantization config design
#2299 opened Jul 16, 2026 by tianleiwu Contributor Loading…
11
Gemma3 CPU export: replace fused SkipSimplifiedLayerNormalization with explicit Add + RMSNorm path
#2296 opened Jul 13, 2026 by Copilot AI • Draft
1
@kunal-vaishnavi
1
Add standard-Quark uint2 -> MatMulNBits (bits=2, float zero-point)
#2295 opened Jul 13, 2026 by thpereir Contributor • Draft
1
Add cross-platform 1DS telemetry to the compiled library (opt-out)
#2293 opened Jul 13, 2026 by bmehta001 Contributor Loading…
@bmehta001
298
Migrating binding to nanobind support
#2289 opened Jul 10, 2026 by themason2011 Loading…
3
Update base speculative decoding implementation (v1)
#2287 opened Jul 9, 2026 by samsat701 Loading…
30
Support gemma-4-12B unified (encoder-free) multimodal model
#2286 opened Jul 9, 2026 by justinchuby Contributor Loading…
3
Inherit top-level session options in pipeline model components
#2282 opened Jul 7, 2026 by qti-mattsinc Contributor Loading…
5
Make pybind11_stubgen type stub generation optional in CMake build
#2281 opened Jul 7, 2026 by Copilot AI • Draft
@themason2011
Contain enable_profiling path to model directory (path traversal hardening)
#2273 opened Jul 6, 2026 by jiafatom Contributor Loading…
4
Avoid disclosing config file contents in parse error messages
#2261 opened Jul 2, 2026 by jiafatom Contributor Loading…
5
Generate pyd type info
#2247 opened Jun 29, 2026 by themason2011 Loading…
20
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
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
Add base speculative decoding implementation (v0)
#2233 opened Jun 19, 2026 by samsat701 Loading…
42
Add path traversal validation
#2222 opened Jun 11, 2026 by apsonawane Contributor Loading…
4
Pipeline-as-Config: structural model dispatch (#2114)
#2210 opened Jun 10, 2026 by justinchuby Contributor • Draft
1
ProTip! Add no:assignee to see everything that’s not assigned.
pFad - Phonifier reborn

Pfad - The Proxy pFad © 2024 Your Company Name. All rights reserved.




Check this box to remove all script contents from the fetched content.



Check this box to remove all images from the fetched content.


Check this box to remove all CSS styles from the fetched content.


Check this box to keep images inefficiently compressed and original size.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy