You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository was archived by the owner on Jul 17, 2024. It is now read-only.
At present it is not possible to use ML.NET with in s #Blazor client application, give that a browser WASM application is in essence a VM with limited resources, it would IMHO be a great for ELL to target client browser possibly emitting Typescript or a C# ELL predictor that can be included I to a C# #Blazor application
The text was updated successfully, but these errors were encountered:
Agreed :-) This may already be possible if you can find an LLVM bitcode to JavaScript generator, like say emscripten. The ELL compiler has a "-bitcode" output option already. But I haven't tried whether this actually works... probably also need to compile the ELL model with "--blas false" so that your bitcode has no openblas dependency.
Is it at all possible to swap out the llvm implementation used by ELL with something like https://github.com/Sonicadvance1/llvm-xtensa to attempt generation of code for Xtensa = ESP8266/ESP32 as well as wasm etc.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
At present it is not possible to use ML.NET with in s #Blazor client application, give that a browser WASM application is in essence a VM with limited resources, it would IMHO be a great for ELL to target client browser possibly emitting Typescript or a C# ELL predictor that can be included I to a C# #Blazor application
The text was updated successfully, but these errors were encountered: