-
Notifications
You must be signed in to change notification settings - Fork 3.1k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add shader key validation step in WebGPU CI pipeline
ep:WebGPU
ort-web webgpu provider
#24243
opened Mar 29, 2025 by
fs-eire
Loading…
Add support for uint8_t as data type for GatherBlockQuantized
#24239
opened Mar 28, 2025 by
sushraja-msft
Loading…
[QNN EP] Add platform-agnostic EP option to specify QNN backend,
backend_type
#24235
opened Mar 28, 2025 by
edgchen1
Loading…
[WIP] Support export of Llama with DynamicCache and transformers>=4.48
#24231
opened Mar 28, 2025 by
xadupre
Loading…
[webgpu] Fix ROUND_PREFER_CEIL issue of Resize operator
#24229
opened Mar 28, 2025 by
xhcao
Loading…
[webgpu] Use 1D dispatch groups for attention
ep:WebGPU
ort-web webgpu provider
#24228
opened Mar 28, 2025 by
qjia7
Loading…
[webgpu] Fix opset-12 softmax nhwc issue
ep:WebGPU
ort-web webgpu provider
#24227
opened Mar 28, 2025 by
xhcao
Loading…
Enable Inference Results Saving in onnx-test-runner
#24210
opened Mar 27, 2025 by
quic-hungjuiw
Loading…
[webgpu] fix the reflect mode issue of Pad
ep:WebGPU
ort-web webgpu provider
#24202
opened Mar 27, 2025 by
xhcao
Loading…
Set shared memory type based on options during the compilation phase
#24196
opened Mar 26, 2025 by
quic-ashigarg
Loading…
Enable mapping of buffers allocated on CPU in the NPU address space
#24195
opened Mar 26, 2025 by
quic-ashigarg
Loading…
Ensure to use correct GPU device in RunSince when it's invoked by new thread
#24192
opened Mar 26, 2025 by
chilo-ms
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.