wizer VS SSVM

> once by the wasm runtime to compile the rust-python wasm

I'm not sure what you mean by that. The runtime doesn't compile WASM, it simply executes it.

There are tools for dealing with interpreter runtime overhead this by pre-initalizing the environment like Wizer[0]. ComponentizeJS[1] uses it to pre-initialize the Spidermoney engine it packages to gain fast startup times (and you can then prune the initialization only code with wasm-opt). As techniques like ComponentizeJS are also being applied for a specific set of interpreted files, you can even prune parts of the interpreter that would never be used for that specific program. If you want to go even further you could record specific execution profiles and optimize further by those.

[0]: https://github.com/bytecodealliance/wizer

[1]: https://github.com/bytecodealliance/ComponentizeJS

Edge functions are typically run intermittently, with their runtime stopped to free up resources between runs. Therefore a big factor is startup and shutdown speed. Containers are pretty bad there. Deno is better, and WASM is unbeatable, especially with things like Wizer[0].

[0]https://github.com/bytecodealliance/wizer

I imagine startup cost could be amortized by something like wizer: https://github.com/bytecodealliance/wizer

There are security benefits to running each request in its own instance, as it helps prevent accidental leaking of state between requests. To avoid doing lots of expensive initializations, we have a tool called wizer which lets users run their program's initialization once, create a snapshot, and then use that snapshot to do fast startups that don't rerun the whole initialization each time.

See https://github.com/bytecodealliance/wizer for an implementation of this approach.

It should probably be named "Making JavaScript to startup fast on WebAssembly", since the runtime speed is not really improved by the approach they exposed.

Besides that I think Wizer [1] is both an elegant and a simple solution to speed up startup speed with Wasm.

[1] - https://github.com/bytecodealliance/wizer#using-wizer-as-a-l...

A similar project, for WebAssembly so with limited scope is this: https://github.com/bytecodealliance/wizer. And somehow similar but limited on LLVM IR a colleague worked on this for Cheerp (the compiler used here as backend): https://github.com/leaningtech/cheerp-meta/wiki/Cheerp-PreExecuter.

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!)...