Enrico Galli
Enrico Galli
When using `types` and the base project needs to override the default `typeRoots`, does that mean they they would need to add `./node_modules` to the `typeRoots`. i.e. ```json { "compilerOptions":...
If we pass the MLContext thru a session options, my understand is that we'll need to a way store the the MLContexts in JS, pass an id to to the...
Even if we pass the MLContext, we would still need to pass the deviceType to the C++ code as it is used to select between NCHW and NHWC. https://github.com/microsoft/onnxruntime/blob/8a98874e7e09e78b3720e291545b2e9823b8151f/onnxruntime/core/providers/webnn/webnn_execution_provider.cc#L31-L32 It...
I have moved the context de-duplication to a singleton in C++.
@fs-eire given that the API changes have landed ( https://github.com/microsoft/onnxruntime/pull/20816 ) should I modify this PR to use the new API directly or should I convert the code back to...
@fs-eire I have updated the PR to use the new API, PTAL.
@guschmue I have fixed the linting issues. That said, I'm concerned about adding `// Copyright (c) Microsoft Corporation. All rights reserved.` to the webnn type declaration file that will eventually...
@Honry, I have changed from `getMLBuffer` to `ensureBuffer` when retrieving outputs. This changed fixes the issue on partitioned graphs.
`MLBuffer` specification has changed. `createBuffer` is now async.
Merged and re-formatted. That said, during internal testing we found an issue when a graph gets partitioned with CPU ops in the middle (ie. `[WebNN EP] -> [MemcpyToHost] -> [CPU...