SSVM VS quickjs

WasmEdge GitHub address: https://github.com/WasmEdge/WasmEdge.

I see that they recently changed the intro of WasmEdge on Github [1] to " WasmEdge is the easiest and fastest way to run LLMs on your own devices. "

Since it's a wasm runtime capable of many things I find bizarre that they now start describing it with a ultra-specific use case

- [1] https://github.com/WasmEdge/WasmEdge

Mmm…

The wasm-nn that this relies on (https://github.com/WebAssembly/wasi-nn) is a proposal that relies of arbitrary plugin backends sending arbitrarily chunks to some vendor implementation. The api is literally like set input, compute, set output.

…and that is totally non portable.

The reason this works, is because it’s relying on the abstraction already implemented in llama.cpp that allows it to take a gguf model and map it to multiple hardware targets,which you can see has been lifted here: https://github.com/WasmEdge/WasmEdge/tree/master/plugins/was...

So..

> Developers can refer to this project to write their machine learning application in a high-level language using the bindings, compile it to WebAssembly, and run it with a WebAssembly runtime that supports the wasi-nn proposal, such as WasmEdge.

Is total rubbish; no, you can’t.

This isn’t portable.

It’s not sandboxed.

If you have a wasm binary you might be able to run it if the version of the runtime you’re using happens to implement the specific ggml backend you need, which it probably doesn’t… because there’s literally no requirement for it to do so.

There’s a lot of “so portable” talk in this article which really seems misplaced.

WasmEdge isn't there yet: https://github.com/WasmEdge/WasmEdge/issues/1122#issuecommen...

Example 1: Analyze the content and risks of each commit in the PR. Then make a summary. https://github.com/WasmEdge/WasmEdge/pull/2394#issuecomment-...

There has also been a few "cloud-native" runtimes based on WASM, like WasmEdge but there's a few others (can't remember their names!)...

It uses service workers to cache static files, by the time it opens up you already free to be offline, try toggle network switch to verify.

It has download link at bottom of the about page ([accdoo.app/about]) which you could then self host it by dropping into any static hosting services.

btw, the Pi feature was by-product from the original App but I won't expand here, if you'd like to learn more, please checkout its two Show HN post (39115559 and 39138957) previously.

[wiki]: https://en.wikipedia.org/wiki/Chudnovsky_algorithm

[quickjs/pi]: https://bellard.org/quickjs/pi.html

[pi_bigint.js]: https://github.com/bellard/quickjs/blob/master/examples/pi_b...

[accdoo.app/about]: https://accdoo.app/about#releases

[39115559]: https://news.ycombinator.com/item?id=39115559

[39138957]: https://news.ycombinator.com/item?id=39138957

Just go with quickjs, I think this is what you are looking for.

https://bellard.org/quickjs/

QuickJS

I think QuickJS, written in C, is a user-"friendly" starting point for implementing ECMA-262. Documentation QuickJS Javascript Engine.

There is a readme on the project's main page: https://bellard.org/quickjs/

The newsworthy bit here is that the activity seemed to have stalled for year or two and now Fabrice pushed a few fixes and made a new release.

Just to demonstrate GitHub repositories do not necessarily reflect upon a programmers' body of work, Fabrice Bellard has one (1) repository published on GitHub, quickjs. Compare the list of work on Bellard's home page https://bellard.org/.

> I am still confused, it's a JavaScript runtime intended to be deployed to JavaScript/Wasm runtimes?

Seemingly.

> Why does a JavaScript runtime need a JavaScript runtime?

Because if you want to create a Service Worker server for CloudFlare Workers and other JavaScript/Wasm runtimes, that's the only option for doing that AFAIK.

FWIW, this isn't a new idea. For example, Figma uses QuickJS (https://bellard.org/quickjs/) for their plug-in runtime: https://www.figma.com/blog/an-update-on-plugin-security/