Pull requests · microsoft/onnxruntime · GitHub
Skip to content

Pull requests: microsoft/onnxruntime

New pull request New
543 Open 18,356 Closed
543 Open 18,356 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

Add position_ids bounds validation to WebGPU/JS RotaryEmbedding kernels
#28214 opened Apr 23, 2026 by titaiwangms Contributor Loading…
18
Bump version to 1.24.6 for release
#28212 opened Apr 23, 2026 by adrastogi Contributor Loading…
[Plugin WebGPU EP] Fix API initialization error handling
#28211 opened Apr 23, 2026 by edgchen1 Contributor Loading…
6
com.microsoft.RotaryEmbedding: validate position_ids are within cos/sin cache bounds
#28206 opened Apr 23, 2026 by Copilot AI • Draft
1
@xadupre
Add size threshold to prevent constant folding from inflating model memory footprint
#28204 opened Apr 23, 2026 by Copilot AI • Draft
1
@xadupre
4
fix: auto-upgrade model opset to 21 for int16/uint16 QDQ quantization
#28202 opened Apr 23, 2026 by Rishi-Dave Contributor Loading…
1
Add regression test for quantize_static with in-memory ModelProto (#23268)
#28201 opened Apr 23, 2026 by Rishi-Dave Contributor Loading…
1
1
[CUDA] PagedAttention: add SM<80 fp16 fallback via memory-efficient attention
#28200 opened Apr 23, 2026 by elwhyjay Contributor Loading…
5
GQA unfused attention with FP32 QK accumulation (fixes #28195)
#28198 opened Apr 23, 2026 by tianleiwu Contributor Loading…
1
11
webgpu: merge batchA into M dimension when batchB==1 ep:WebGPU ort-web webgpu provider
#28197 opened Apr 23, 2026 by xhcao Contributor Loading…
3
Bump fast-xml-parser and react-native in /js/react_native/e2e dependencies Pull requests that update a dependency file javascript Pull requests that update Javascript code
#28193 opened Apr 22, 2026 by dependabot Bot Loading…
Add workflow to replace Windows GPU Doc Gen CI Pipeline
#28192 opened Apr 22, 2026 by tianleiwu Contributor Loading…
2
Make sure in memory initialziers are not propagated externally
#28189 opened Apr 22, 2026 by yuslepukhin Member Loading…
1
3
Reject recursive local function definitions during model load
#28187 opened Apr 22, 2026 by tianleiwu Contributor Loading…
5
Harden ORT FlatBuffer model loader against malformed buffers
#28186 opened Apr 22, 2026 by tianleiwu Contributor Loading…
7
Add CPU QMoE 2-bit support and LUT GEMM fast path
#28185 opened Apr 22, 2026 by tianleiwu Contributor • Draft
3 of 4 tasks
[CoreML EP] Add QuickGelu support
#28184 opened Apr 22, 2026 by maxwbuckley Loading…
1
9
[CoreML EP] Add HardSigmoid support
#28182 opened Apr 22, 2026 by maxwbuckley Loading…
1
11
fix: add missing BackendKernelSelectorConfig parameter to QNBitGemmPackQuantBDataSize_Lasx
#28179 opened Apr 22, 2026 by Rishi-Dave Contributor Loading…
1
1
fix: support N-D weights with unit leading dims in MatMulNBitsQuantizer
#28178 opened Apr 22, 2026 by Rishi-Dave Contributor Loading…
1
5
Fix heap OOB write in EmbedLayerNormalizationShapeInference
#28176 opened Apr 22, 2026 by Copilot AI • Draft
1
@xadupre
3
webgpu: use naive reduction ep:WebGPU ort-web webgpu provider
#28174 opened Apr 22, 2026 by xhcao Contributor Loading…
3
[WebNN] Rename roundingType to outputShapeRounding for pool2d ops ep:WebNN WebNN execution provider
#28172 opened Apr 22, 2026 by Honry Contributor Loading…
4
[OVEP] Updating OV version to 2026.1.0
#28170 opened Apr 22, 2026 by preetha-intel Contributor Loading…
[Core] Add correctness tests for SpaceToDepth and MobileClip Attention fusion
#28168 opened Apr 22, 2026 by hariharans29 Member Loading…
3
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.