SSVM
wasm32-wasi-benchmark
| SSVM | wasm32-wasi-benchmark | |
|---|---|---|
| 50 | 4 | |
| 7,952 | 36 | |
| 1.7% | - | |
| 9.7 | 10.0 | |
| 3 days ago | over 2 years ago | |
| C++ | C++ | |
| Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
SSVM
- A WASM runtime for running LLMs locally
-
Time-series data ingestion from Rust WebAssembly application, leveraging GreptimeDB and WasmEdge
WasmEdge GitHub address: https://github.com/WasmEdge/WasmEdge.
-
Orca-2-13B Runs Directly on Rust+WASM – No Python/C++ Hassles
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
-
Run LLMs on my own Mac fast and efficient Only 2 MBs
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.
- Security Slam 2023: Contribute to WasmEdge and Elevate Open Source Security
-
Requiem for a Stringref
WasmEdge isn't there yet: https://github.com/WasmEdge/WasmEdge/issues/1122#issuecommen...
- Should You Be Scared of Unix Signals?
- WasmEdge 0.13.0: Unified CLI, ARM Support and Migrating Extensions to Plugins
-
ChatGPT-powered code review bot to boost your PR merge. Deploy in 5 mins
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-...
-
Cloud, Why So Difficult?
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!)...
wasm32-wasi-benchmark
-
Towards a modern Web stack (by Ian Hickson, author of the HTML5 spec and current Flutter tech lead)
On other benchmarks I'm seeing numbers closer to 20% slower, e.g. https://github.com/wasm3/wasm3/blob/main/docs/Performance.md and https://github.com/second-state/wasm32-wasi-benchmark. It's numerical code, which is the best case scenario for a native binary. It's much closer on an average web app or server workload, e.g. https://krausest.github.io/js-framework-benchmark/current.html - you can find WASM frameworks that beat most JS frameworks on there, but that is not as impressive considering the state of the JS ecosystem. Overall, it's already under 50%, and there is still plenty of room for improvement.
-
WasmEdge, a high-performance WebAssembly runtime with Rust first APIs and Features (Wasm on server side)
Source code of test cases: https://github.com/second-state/wasm32-wasi-benchmark
-
WasmEdge
We did benchmarks last year but not recently (Will update if there are new ones).
Paper: A Lightweight Design for High-performance Serverless Computing, published on IEEE Software, Jan 2021. https://arxiv.org/abs/2010.07115
Article: Performance Analysis for Arm vs. x86 CPUs in the Cloud, published on infoQ.com, Jan 2021. https://www.infoq.com/articles/arm-vs-x86-cloud-performance/
Source code of test cases: https://github.com/second-state/wasm32-wasi-benchmark
What are some alternatives?
wasmer - 🚀 The leading Wasm Runtime supporting WASIX, WASI and Emscripten
wasmtime - A fast and secure runtime for WebAssembly
wasm3 - 🚀 A fast WebAssembly interpreter and the most universal WASM runtime
aws-lambda-wasm-runtime - A template project for building high-performance, portable, and safe serverless functions in AWS Lambda.
rusty_v8 - Rust bindings for the V8 JavaScript engine
WAVM - WebAssembly Virtual Machine
cpp_weekly - The official C++ Weekly Repository. Code samples and notes of future / past episodes will land here at various times. PR's will be accepted in some cases.
dapr-wasm - A template project to demonstrate how to run WebAssembly functions as sidecar microservices in dapr
spin - Spin is the open source developer tool for building and running serverless applications powered by WebAssembly.
WasmEdge-go - The GO language SDK and API for WasmEdge
buildah - A tool that facilitates building OCI images.