From 71320d95b8c6d43f9af7f44e18b1839db85d89b4 Mon Sep 17 00:00:00 2001 From: Andrew Brown Date: Mon, 28 Oct 2024 11:51:50 -0700 Subject: [PATCH] Update snapshot version (#82) --- ml.md | 16 ++++++++-------- wit/wasi-nn.wit | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/ml.md b/ml.md index 5332027..bc58e87 100644 --- a/ml.md +++ b/ml.md @@ -9,14 +9,14 @@ Then, the user passes tensor inputs to the graph, computes the -

Import interface wasi:nn/tensor@0.2.0-rc-2024-08-19

+

Import interface wasi:nn/tensor@0.2.0-rc-2024-10-28

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

Types

@@ -90,7 +90,7 @@ containing a single value, use [1] for the tensor dimensions.

-

Import interface wasi:nn/errors@0.2.0-rc-2024-08-19

+

Import interface wasi:nn/errors@0.2.0-rc-2024-10-28

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

Types

@@ -158,7 +158,7 @@ e.g., cannot access a hardware feature requested -

Import interface wasi:nn/inference@0.2.0-rc-2024-08-19

+

Import interface wasi:nn/inference@0.2.0-rc-2024-10-28

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

@@ -193,7 +193,7 @@ graph inputs and outputs.

-

Import interface wasi:nn/graph@0.2.0-rc-2024-08-19

+

Import interface wasi:nn/graph@0.2.0-rc-2024-10-28

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

diff --git a/wit/wasi-nn.wit b/wit/wasi-nn.wit index f5c3054..277f98d 100644 --- a/wit/wasi-nn.wit +++ b/wit/wasi-nn.wit @@ -1,4 +1,4 @@ -package wasi:nn@0.2.0-rc-2024-08-19; +package wasi:nn@0.2.0-rc-2024-10-28; /// `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