World ml

wasi-nn is a WASI API for performing machine learning (ML) inference. The API is not (yet) capable of performing ML training. WebAssembly programs that want to use a host's ML capabilities can access these capabilities through wasi-nn's core abstractions: graphs and tensors. A user loads an ML model -- instantiated as a graph -- to use in an ML backend. Then, the user passes tensor inputs to the graph, computes the inference, and retrieves the tensor outputs.

This example world shows how to use these primitives together.

Import interface wasi:nn/tensor

All inputs and outputs to an ML inference are represented as tensors.

Types

type tensor-dimensions

tensor-dimensions

The dimensions of a tensor.

The array length matches the tensor rank and each element in the array describes the size of each dimension

enum tensor-type

The type of the elements in a tensor.

Enum Cases

type tensor-data

tensor-data

The tensor data.

Initially conceived as a sparse representation, each empty cell would be filled with zeros and the array length must match the product of all of the dimensions and the number of bytes in the type (e.g., a 2x2 tensor with 4-byte f32 elements would have a data array of length 16). Naturally, this representation requires some knowledge of how to lay out data in memory--e.g., using row-major ordering--and could perhaps be improved.

record tensor

Record Fields

Import interface wasi:nn/errors

TODO: create function-specific errors (https://github.com/WebAssembly/wasi-nn/issues/42)

Types

enum error

Enum Cases

Import interface wasi:nn/graph

A graph is a loaded instance of a specific ML model (e.g., MobileNet) for a specific ML framework (e.g., TensorFlow):

Types

type error

error

#### `type tensor` [`tensor`](#tensor)

#### `type graph` `u32`

An execution graph for performing inference (i.e., a model).

TODO: replace with resource (https://github.com/WebAssembly/wasi-nn/issues/47).

enum graph-encoding

Describes the encoding of the graph. This allows the API to be implemented by various backends that encode (i.e., serialize) their graph IR with different formats.

Enum Cases

enum execution-target

Define where the graph should be executed.

Enum Cases

type graph-builder

graph-builder

The graph initialization data.

This gets bundled up into an array of buffers because implementing backends may encode their graph IR in parts (e.g., OpenVINO stores its IR and weights separately).

Functions

load: func

Load a graph from an opaque sequence of bytes to use for inference.

Params
Return values

load-by-name: func

Load a graph by name.

How the host expects the names to be passed and how it stores the graphs for retrieval via this function is implementation-specific. This allows hosts to choose name schemes that range from simple to complex (e.g., URLs?) and caching mechanisms of various kinds.

Params
Return values

Import interface wasi:nn/inference

An inference "session" is encapsulated by a graph-execution-context. This structure binds a graph to input tensors before compute-ing an inference:

Types

type error

error

#### `type tensor` [`tensor`](#tensor)

#### `type tensor-data` [`tensor-data`](#tensor_data)

#### `type graph` [`graph`](#graph)

#### `type graph-execution-context` `u32`

Bind a `graph` to the input and output tensors for an inference.

TODO: this is no longer necessary in WIT (https://github.com/WebAssembly/wasi-nn/issues/43)

Functions

init-execution-context: func

Create an execution instance of a loaded graph.

Params
Return values

set-input: func

Define the inputs to use for inference.

Params
Return values

compute: func

Compute the inference on the given inputs.

Note the expected sequence of calls: set-input, compute, get-output. TODO: this expectation could be removed as a part of https://github.com/WebAssembly/wasi-nn/issues/43.

Params
Return values

get-output: func

Extract the outputs after inference.

Params
Return values