mingmingtasd

[L139](https://github.com/otcshare/chromium-src/blob/webml/third_party/ienn/src/ie_execution.cpp#L139) in chromium repo should be as: `memcpy(input_blob->buffer(), input_data_[i].buffer), input_data_[i].length);` We needn't change blob's data type. And we can remove `element::f16` in [L209](https://github.com/otcshare/chromium-src/blob/webml/third_party/ienn/src/ie_compilation.cpp#L209).

[WASM/WebGL] Failed to run WASM/WebGL backend with intel.github.io on Windows

4

I find that there is something wrong with intel.github.io. For WASM backend, it reports that "Backend 'wasm' has not yet been initialized. Make sure to await tf.ready() or await tf.setBackend()...

Our API now use explicit padding to process the 'valid' and 'same' PaddingCode, will cause that some new OpenVINO models (IR v10) such as FaceNet fail to run, error is...

[NNAPI] Upgrade Android NDK and implement burst executions API

6

This issue created to track this [Android 10 issue ](https://github.com/intel/webml-polyfill/issues/1060) and to find if there is another way to resolve it. Two steps need to follow: 1. Upgrade Android NDK...

Squeezenet1.0 models give wrong prediction results

3

# Bug Report ### Which model does this pertain to? All squeezenet 1.0 models from https://github.com/onnx/models/tree/main/validated/vision/classification/squeezenet ### Describe the bug These squeezenet 1.0 models can't provide correct prediction results: ###...

Add support for MCDM/DXCore devices.

4

We need DXCore to enumerate VPU device, so should we replace IDXGIAdapter with IDCoreAdapter? wdyt? @bjjones @bbernhar @[junwei](https://github.com/fujunwei)