📄️ The wasmedge CLI
After installing WasmEdge, you can use the wasmedge CLI to execute WASM files. We will cover how to run WASM files with WasmEdge on your machine and Docker images.
📄️ wasmedge run CLI
After installation, users can execute the wasmedge run command.
📄️ The AoT Compiler
After installation, users can execute the wasmedge compile command.
📄️ Docker + WASM
The Docker Desktop distributes with the WasmEdge Runtime embedded. That allows developers to build, share and run very lightweight containers (i.e., a scratch empty container with only the .wasm file without any Linux OS libraries or files) through Docker tools. Those "WASM containers" are fully OCI-compliant and hence can be managed by Docker Hub. They are cross-platform and can run on any OS / CPU Docker supports (the OS and CPU platform is wasi/wasm). But most importantly, they are 1/10 of the size of a comparable Linux container and start up in 1/10 of the time, as the WASM containers do not need to bundle and start Linux libraries and services.
📄️ Docker + WASM + GPU
This is a completely new approach, adopting Docker + Crun with Wasmedge + CDI to enable the usage of host GPU devices. The reason for not continuing with the use of runwasi as the wasm runtime within Docker from the previous chapter is due to considerations of the current stage of support for CDI and the compatibility approach.
📄️ Podman + WASM + GPU
Podman + Crun with Wasmedge + CDI to enable the usage of host GPU devices. Most of the steps are the same with docker + wasm + gpu, except for the installation of Podman and execution command. If the following steps have already been executed before, you could just skip them.