github
/
cranelift
mirror of https://github.com/bytecodealliance/wasmtime.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
9881 Commits
49 Branches
140 Tags
128 MiB
Tree: b306368565
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'b306368565'
${ noResults }
cranelift/ci/run-wasi-nn-example.sh

46 lines
2.2 KiB
Raw Normal View History

Add an initial wasi-nn implementation for Wasmtime (#2208) * Add an initial wasi-nn implementation for Wasmtime This change adds a crate, `wasmtime-wasi-nn`, that uses `wiggle` to expose the current state of the wasi-nn API and `openvino` to implement the exposed functions. It includes an end-to-end test demonstrating how to do classification using wasi-nn: - `crates/wasi-nn/tests/classification-example` contains Rust code that is compiled to the `wasm32-wasi` target and run with a Wasmtime embedding that exposes the wasi-nn calls - the example uses Rust bindings for wasi-nn contained in `crates/wasi-nn/tests/wasi-nn-rust-bindings`; this crate contains code generated by `witx-bindgen` and eventually should be its own standalone crate * Test wasi-nn as a CI step This change adds: - a GitHub action for installing OpenVINO - a script, `ci/run-wasi-nn-example.sh`, to run the classification example
4 years ago
#!/bin/bash
# The following script demonstrates how to execute a machine learning inference using the wasi-nn module optionally
# compiled into Wasmtime. Calling it will download the necessary model and tensor files stored separately in $FIXTURE
# into $TMP_DIR (optionally pass a directory with existing files as the first argument to re-try the script). Then,
# it will compile the example code in crates/wasi-nn/tests/example into a Wasm file that is subsequently
# executed with the Wasmtime CLI.
set -e
WASMTIME_DIR=$(dirname "$0" | xargs dirname)
wasi-nn: use the MobileNet model instead of AlexNet The MobileNet model is significantly smaller in size (14MB) than the AlexNet model (233MB); this change should reduce bandwidth used during CI.
4 years ago
FIXTURE=https://github.com/intel/openvino-rs/raw/main/crates/openvino/tests/fixtures/mobilenet
Avoid removing wasi-nn temp directory when specified (#2465) Since downloading the wasi-nn artifacts take a bit of time, the example script's first argument serves as a directory to reuse for running this script. This change cleans up temporary directories only when a directory was not specified.
4 years ago
if [ -z "${1+x}" ]; then
# If no temporary directory is specified, create one.
TMP_DIR=$(mktemp -d -t ci-XXXXXXXXXX)
REMOVE_TMP_DIR=1
else
# If a directory was specified, use it and avoid removing it.
TMP_DIR=$(realpath $1)
REMOVE_TMP_DIR=0
fi
Add an initial wasi-nn implementation for Wasmtime (#2208) * Add an initial wasi-nn implementation for Wasmtime This change adds a crate, `wasmtime-wasi-nn`, that uses `wiggle` to expose the current state of the wasi-nn API and `openvino` to implement the exposed functions. It includes an end-to-end test demonstrating how to do classification using wasi-nn: - `crates/wasi-nn/tests/classification-example` contains Rust code that is compiled to the `wasm32-wasi` target and run with a Wasmtime embedding that exposes the wasi-nn calls - the example uses Rust bindings for wasi-nn contained in `crates/wasi-nn/tests/wasi-nn-rust-bindings`; this crate contains code generated by `witx-bindgen` and eventually should be its own standalone crate * Test wasi-nn as a CI step This change adds: - a GitHub action for installing OpenVINO - a script, `ci/run-wasi-nn-example.sh`, to run the classification example
4 years ago
# Inform the environment of OpenVINO library locations. Then we use OPENVINO_INSTALL_DIR below to avoid building all of
# OpenVINO from source (quite slow).
Fix for issue #3948 (#3956) Updates the OpenVINO backend for wasi-nn to pre-configure all inputs as `NHWC`. This is not a long-term fix but no worse than the status quo, which configures all input tensors to the same layout. This change updates the CI script to use the latest version of OpenVINO. Closes #3948. Co-authored-by: Andrew Brown <andrew.brown@intel.com>
3 years ago
source /opt/intel/openvino_2021/bin/setupvars.sh
Add an initial wasi-nn implementation for Wasmtime (#2208) * Add an initial wasi-nn implementation for Wasmtime This change adds a crate, `wasmtime-wasi-nn`, that uses `wiggle` to expose the current state of the wasi-nn API and `openvino` to implement the exposed functions. It includes an end-to-end test demonstrating how to do classification using wasi-nn: - `crates/wasi-nn/tests/classification-example` contains Rust code that is compiled to the `wasm32-wasi` target and run with a Wasmtime embedding that exposes the wasi-nn calls - the example uses Rust bindings for wasi-nn contained in `crates/wasi-nn/tests/wasi-nn-rust-bindings`; this crate contains code generated by `witx-bindgen` and eventually should be its own standalone crate * Test wasi-nn as a CI step This change adds: - a GitHub action for installing OpenVINO - a script, `ci/run-wasi-nn-example.sh`, to run the classification example
4 years ago
# Build Wasmtime with wasi-nn enabled; we attempt this first to avoid extra work if the build fails.
OPENVINO_INSTALL_DIR=/opt/intel/openvino cargo build -p wasmtime-cli --features wasi-nn
# Download all necessary test fixtures to the temporary directory.
wasi-nn: use the MobileNet model instead of AlexNet The MobileNet model is significantly smaller in size (14MB) than the AlexNet model (233MB); this change should reduce bandwidth used during CI.
4 years ago
wget --no-clobber $FIXTURE/mobilenet.bin --output-document=$TMP_DIR/model.bin
wget --no-clobber $FIXTURE/mobilenet.xml --output-document=$TMP_DIR/model.xml
wget --no-clobber $FIXTURE/tensor-1x224x224x3-f32.bgr --output-document=$TMP_DIR/tensor.bgr
Add an initial wasi-nn implementation for Wasmtime (#2208) * Add an initial wasi-nn implementation for Wasmtime This change adds a crate, `wasmtime-wasi-nn`, that uses `wiggle` to expose the current state of the wasi-nn API and `openvino` to implement the exposed functions. It includes an end-to-end test demonstrating how to do classification using wasi-nn: - `crates/wasi-nn/tests/classification-example` contains Rust code that is compiled to the `wasm32-wasi` target and run with a Wasmtime embedding that exposes the wasi-nn calls - the example uses Rust bindings for wasi-nn contained in `crates/wasi-nn/tests/wasi-nn-rust-bindings`; this crate contains code generated by `witx-bindgen` and eventually should be its own standalone crate * Test wasi-nn as a CI step This change adds: - a GitHub action for installing OpenVINO - a script, `ci/run-wasi-nn-example.sh`, to run the classification example
4 years ago
# Now build an example that uses the wasi-nn API.
pushd $WASMTIME_DIR/crates/wasi-nn/examples/classification-example
cargo build --release --target=wasm32-wasi
cp target/wasm32-wasi/release/wasi-nn-example.wasm $TMP_DIR
popd
# Run the example in Wasmtime (note that the example uses `fixture` as the expected location of the model/tensor files).
wasi-nn: turn it on by default (#2859) * wasi-nn: turn it on by default This change makes the wasi-nn Cargo feature a default feature. Previously, a wasi-nn user would have to build a separate Wasmtime binary (e.g. `cargo build --features wasi-nn ...`) to use wasi-nn and the resulting binary would require OpenVINO shared libraries to be present in the environment in order to run (otherwise it would fail immediately with linking errors). With recent changes to the `openvino` crate, the wasi-nn implementation can defer the loading of the OpenVINO shared libraries until runtime (i.e., when the user Wasm program calls `wasi_ephemeral_nn::load`) and display a user-level error if anything goes wrong (e.g., the OpenVINO libraries are not present on the system). This runtime-linking addition allows the wasi-nn feature to be turned on by default and shipped with upcoming releases of Wasmtime. This change should be transparent for users who do not use wasi-nn: the `openvino` crate is small and the newly-available wasi-nn imports only affect programs in which they are used. For those interested in reviewing the runtime linking approach added to the `openvino` crate, see https://github.com/intel/openvino-rs/pull/19. * wasi-nn spec path: don't use canonicalize * Allow dependencies using the ISC license The ISC license should be [just as permissive](https://choosealicense.com/licenses/isc) as MIT, e.g., with no additional limitations. * Add a `--wasi-modules` flag This flag controls which WASI modules are made available to the Wasm program. This initial commit enables `wasi-common` by default (equivalent to `--wasi-modules=all`) and allows `wasi-nn` and `wasi-crypto` to be added in either individually (e.g., `--wasi-modules=wasi-nn`) or as a group (e.g., `--wasi-modules=all-experimental`). * wasi-crypto: fix unused dependency Co-authored-by: Pat Hickey <pat@moreproductive.org>
4 years ago
cargo run -- run --mapdir fixture::$TMP_DIR $TMP_DIR/wasi-nn-example.wasm --wasi-modules=experimental-wasi-nn
Add an initial wasi-nn implementation for Wasmtime (#2208) * Add an initial wasi-nn implementation for Wasmtime This change adds a crate, `wasmtime-wasi-nn`, that uses `wiggle` to expose the current state of the wasi-nn API and `openvino` to implement the exposed functions. It includes an end-to-end test demonstrating how to do classification using wasi-nn: - `crates/wasi-nn/tests/classification-example` contains Rust code that is compiled to the `wasm32-wasi` target and run with a Wasmtime embedding that exposes the wasi-nn calls - the example uses Rust bindings for wasi-nn contained in `crates/wasi-nn/tests/wasi-nn-rust-bindings`; this crate contains code generated by `witx-bindgen` and eventually should be its own standalone crate * Test wasi-nn as a CI step This change adds: - a GitHub action for installing OpenVINO - a script, `ci/run-wasi-nn-example.sh`, to run the classification example
4 years ago
Avoid removing wasi-nn temp directory when specified (#2465) Since downloading the wasi-nn artifacts take a bit of time, the example script's first argument serves as a directory to reuse for running this script. This change cleans up temporary directories only when a directory was not specified.
4 years ago
# Clean up the temporary directory only if it was not specified (users may want to keep the directory around).
if [[ $REMOVE_TMP_DIR -eq 1 ]]; then
rm -rf $TMP_DIR
wasi-nn: use the MobileNet model instead of AlexNet The MobileNet model is significantly smaller in size (14MB) than the AlexNet model (233MB); this change should reduce bandwidth used during CI.
4 years ago
fi