tensorflow
tfjs-backend-wasm init with WebAssembly.Module
Please make sure that this is a feature request. As per our GitHub Policy, we only address code/doc bugs, performance issues, feature requests and build/installation issues on GitHub. tag:feature_template
System information
- TensorFlow.js version (you are using): 4.16.0
- Are you willing to contribute it (Yes/No): I try it. Maybe but I weak English and this project is complicate. There's a good chance that the code will not be pretty to someone in the know.
Describe the feature and the current behavior/state.
Current, we use setWasmPaths init func but, cloudflare workers cannot create WebAssembly.Module.
Cloudflare workers directly import WebAssembly.Module from path.
Please add init func from WebAssembly.Module.
Will this change the current api? How? SetWasmModulePath function or setWasmPaths to accept WebAssembly.Module as an argument as well.
Who will benefit with this feature? AI on cloudflare worker very fast because SIMD.
Any Other info. Cloudflare Workers can use WebGPU but not all server yet.
