A key differentiator of WasmEdge from other WebAssembly runtimes is its support for non-standard extensions. The WebAssembly System Interface (WASI) provides a mechanism for developers to extend WebAssembly efficiently and securely. The WasmEdge team created the following WASI-like extensions based on real-world customer demands.
- Tensorflow. Developers can write Tensorflow inference functions using a simple Rust API, and then run the function securely and at native speed inside WasmEdge.
- Image processing. WasmEdge uses native libraries to manipulate images for computer vision tasks.
- KV Storage. The WasmEdge storage interface allows WebAssembly programs to read and write a key value store.
- Network sockets. WasmEdge applications can access the network sockets for TCP and HTTP connections.
- Command interface. WasmEdge enables webassembly functions execute native commands in the host operating system. It supports passing arguments, environment variables,
STDOUTpipes, and security policies for host access.
- Ethereum. The WasmEdge Ewasm extension supports Ethereum smart contracts compiled to WebAssembly. It is a leading implementation for Ethereum flavored WebAssembly (Ewasm).
- Substrate. The Pallet allows WasmEdge to act as an Ethereum smart contract execution engine on any Substrate based blockchains.
|WasmEdge-Image||Image host function extension with shared library.||since ||since ||since ||since |
|WasmEdge-Tensorflow||TensorFlow host function extension with shared library.||TensorFlow and TensorFlow-Lite since ||TensorFlow-Lite since ||TensorFlow-Lite since ||TensorFlow and TensorFlow-Lite since |
|WasmEdge-Tensorflow-Tools||WasmEdge CLI tools with TensorFlow and image extension.||since ||since ||since ||since |