-
Notifications
You must be signed in to change notification settings - Fork 3.3k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[webgpu] support smooth softmax for non-FA GQA implementation
#25285
opened Jul 4, 2025 by
fs-eire
Loading…
[QNN EP] Upgrade QNN to 2.36.0
ep:QNN
issues related to QNN exeution provider
#25283
opened Jul 3, 2025 by
qti-jkilpatrick
Loading…
Fix INT32 bias overflow in QOperator INT8 symmetric quantization by adjusting weight scale and requantizing
#25278
opened Jul 3, 2025 by
Bonoy0328
Loading…
Move buffer release or cache from OnRefresh to ReleaseBuffer in BucketCacheManager
ep:WebGPU
ort-web webgpu provider
#25276
opened Jul 3, 2025 by
feich-ms
Loading…
Upgrade xnnpack to latest
ep:Xnnpack
issues related to XNNPACK EP
#25275
opened Jul 3, 2025 by
fanchenkong1
Loading…
Add OrtEpFactory::GetVersion and store EP version in EP metadata.
#25272
opened Jul 3, 2025 by
edgchen1
Loading…
fix webgpu dequantize_linear ut
ep:WebGPU
ort-web webgpu provider
#25271
opened Jul 3, 2025 by
guschmue
Loading…
Add option for GraphViewerToProto serialization to skip writing data
#25263
opened Jul 2, 2025 by
kevinch-nv
Loading…
[webgpu] extend cast version to 23
ep:WebGPU
ort-web webgpu provider
#25235
opened Jul 1, 2025 by
xhcao
Loading…
[webgpu] Refactor ort-web webgpu provider
MatMulNBitsWideTileProgram
shader
ep:WebGPU
#25233
opened Jul 1, 2025 by
daijh
Loading…
Previous Next
ProTip!
Add no:assignee to see everything that’s not assigned.