cmd/

Command enginetest is a minimal engine worker, as the playground's: the engine's browser executor (one Web Worker per container, the SAB bridge) with this module's host modules, wasi:webgpu and wasi-nn (CPU and WebGPU backends).

Command ffwait is the control for go-wasmcontainers/gpu#25: a standalone page (no engine, no container) that times each await of a WebGPU submit + read-back, in the page and in a Worker, and prints the page's JSON report.

Command gpuprobe asks a real browser, through Playwright, what WebGPU it offers a page: whether navigator.gpu exists (in a window and in a worker), and the adapter's vendor, architecture and whether it is a fallback (software) adapter.

Command llmbaseline measures the reference speeds that in-container WebGPU inference is compared against (docs/llm-design.md, step 0): llama.cpp on one CPU thread (and Metal, as context), and WebLLM in Chrome for Testing on the Apple GPU, interleaved round by round with the load checked before each run.

Command loopsweep finds the smallest loop-budget work (gpubatch layer 4) with which a set of e2e tests still passes with zero truncations: it runs them at LoopWork = 2^k for k from --from to --to, with the per-loop floor at 1 so that the floor masks nothing, and prints one line per k.

Command mnistpng extracts one picture of the MNIST test set (IDX files, gzipped, as published by Y. LeCun, C. Cortes and C. Burges; CC BY-SA 3.0) to a 28x28 grayscale PNG and prints its label, so the mnist example classifies a real handwritten digit whose answer is known.

Command onnxvendor copies the ONNX node tests this repository's onnx package can run into onnx/testdata/node: from a checkout of github.com/onnx/onnx (v1.22.0 is the last tag that ships onnx/backend/test/data/node), every test whose model decodes, uses only supported operators and passes onnx.NewSession.

Command webtest runs in a browser Web Worker (as the playground's engine worker does) and checks the WebGPU wasi-nn backend against the ONNX node tests and MNIST-12: for each case it fetches the model and its test data from the page's origin, runs it through webgpu.Backend, compares with the reference (rtol 1e-3, atol 1e-7, the ONNX backend's tolerances) and posts a JSON report: the adapter, and every case's result.

Command witgen writes the core imports of a WIT interface for Go guests (GOOS=wasip1): one //go:wasmimport per function and resource drop, with its Canonical ABI core signature (package wit), and a table from import name to a call taking and returning core values as uint64.