Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
661 Open 19,173 Closed
661 Open 19,173 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: drop orphaned sharded_moe
#31139 opened Jul 29, 2026 by GaetanLepage Loading…
2
[OpenVINO EP] Fix get/set_float_initializer_data for raw_data backed float initializers
#31138 opened Jul 29, 2026 by wangw-1991 Contributor Loading…
2
Auto-generated baselines by 1ES Pipeline Templates
#31136 opened Jul 29, 2026 by microsoft-github-policy-service Bot Loading…
1
[WebGPU EP] Support int64 for Concat
#31049 opened Jul 29, 2026 by miaobin Contributor Loading…
2
Delay load shell32
#30889 opened Jul 29, 2026 by shiyi9801 Contributor Loading…
5
[WebGPU] Loosen the conditions to use Split-K on Panther Lake iGPU
#30514 opened Jul 29, 2026 by Jiawei-Shao Contributor Loading…
2
[WebGPU EP] Add PRelu support
#30512 opened Jul 28, 2026 by AngelGalindo7 Loading…
1
8
Build onnxruntime_providers as an object library for shared-lib builds
#30511 opened Jul 28, 2026 by rvandermeulen Contributor Loading…
1
Add OrtEp-level conformance checks for plugin EPs
#29924 opened Jul 28, 2026 by GopalakrishnanN Contributor Loading…
2
Docs: document macOS CoreML EP builds and packages
#29923 opened Jul 28, 2026 by sankalpsthakur Loading…
2
Add BFloat16 support for PackedAttention, PackedMultiHeadAttention, ShardedMoE (CUDA EP)
#29922 opened Jul 28, 2026 by namgyu-youn Contributor Loading…
1
Document get_provider_graph_assignment_info for EP fallback detection
#29921 opened Jul 28, 2026 by davidnichols-ops Loading…
2
Fix MLAS ARM64 detection for Android on device native Termux builds
#29920 opened Jul 28, 2026 by GlitchintheAnomaly Loading…
1
[CUDA] Fuse MoE softmax/top-k into the expert-map prologue at decode
#29919 opened Jul 28, 2026 by tianleiwu Contributor Loading…
3
[WebGPU EP] Gate int64 Clip kernel behind enable_int64
#29918 opened Jul 28, 2026 by mingmingtasd Contributor Loading…
7
[QNN EP] Enable perf_test QnnHtpShared zero-copy input on plugin-EP path
#29917 opened Jul 28, 2026 by chunghow-qti Contributor Loading…
Fix TensorScatter CPU security issue
#29916 opened Jul 28, 2026 by nenad1002 Contributor Loading…
2
Drive EP conformance coverage from the provider registry
#29915 opened Jul 28, 2026 by GopalakrishnanN Contributor Loading…
2
[CUDA] Extend PagedAttention to support MLA, Quantized KV Cache, QK Norm, Head Sink and Slot Mapping
#29912 opened Jul 27, 2026 by tianleiwu Contributor • Draft
4
[CUDA] Address feedback for block-scaled MatMul and MoE GEMV
#29910 opened Jul 27, 2026 by tianleiwu Contributor Loading…
2 of 3 tasks
10
Upgrade Protobuf to v33.6
#29906 opened Jul 27, 2026 by Copilot AI • Draft
1
@tianleiwu
1
[CUDA] GQA support sliding_window_cache
#29904 opened Jul 27, 2026 by tianleiwu Contributor Loading…
3
Register the BFloat16 IsNaN CPU kernel for opsets 13 to 19
#29902 opened Jul 27, 2026 by blazingphoenix7 Contributor Loading…
1
[MLAS] Integrate symmetric Q4 SME2 kernels in MatMulNBits
#29898 opened Jul 27, 2026 by martin-klacer-arm Contributor Loading…
5
[OpenVINO EP] Support dot-separated KV cache tensor names in stateful (CausalLM) transform
#29895 opened Jul 27, 2026 by zlma7001 Loading…
8
ProTip! Type g i on any issue or pull request to go back to the issue listing page.