Registry / ai-ml / onnxruntime-common

onnxruntime-common

library1.24.3jsnpmunverified

onnxruntime-common serves as the foundational JavaScript API layer for the ONNX Runtime ecosystem, providing shared types, interfaces, and core functionalities. It is designed to be consumed indirectly by platform-specific packages like `onnxruntime-node`, `onnxruntime-web`, and `onnxruntime-react-native`, rather than being used directly by end-user applications. The current stable version is 1.24.3, with frequent patch releases addressing bug fixes, security enhancements, and execution provider updates, as evidenced by recent 1.24.x versions. Its primary differentiator is enabling a consistent programming model across various JavaScript environments, abstracting away platform-specific implementations and ensuring interoperability for machine learning inference.

ai-ml

npm install onnxruntime-common

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · ONNXRUNTIME-COMMON

onnxruntime-common

ai-mljavascriptv1.24.3

Install

—

Import

—

Disk

—

Pass rate

0/ 6

Env Coverage0 / 6

glibc

18–22

musl

18–22

Install & Compatibility

Where this runs

tested against v? · npm install

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

node 18–226 runs

build_error

glibc

node 18–226 runs

build_error

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

InferenceSession

✓ import { InferenceSession } from 'onnxruntime-common';

Common interface/class for inference sessions, typically instantiated via platform-specific packages (e.g., `onnxruntime-node`).

Tensor

✓ import { Tensor } from 'onnxruntime-common';

Represents a multi-dimensional array, the fundamental data structure for model inputs and outputs across all ONNX Runtime JavaScript environments.

SessionOptions

✓ import { SessionOptions } from 'onnxruntime-common';

Interface for configuring an InferenceSession, including execution providers, logging, and other runtime parameters. Used when creating a session with platform-specific `create()` methods.

Debug

Known issues

breakingPython 3.10 wheels are no longer published for ONNX Runtime. Users must upgrade their Python environment to 3.11+ when using Python bindings. Python 3.14 support has been added.

fix

Upgrade Python environments to version 3.11 or newer to ensure compatibility with ONNX Runtime Python packages.

affects: >=1.24.1

breakingx86_64 binaries for macOS/iOS are no longer provided, and the minimum macOS version supported for ONNX Runtime has been raised to 14.0.

fix

Ensure development and deployment environments for macOS/iOS target ARM64 architecture and run macOS 14.0 (Sonoma) or newer.

affects: >=1.24.1

breakingONNX Runtime GPU packages now explicitly require CUDA 12.x. Packages built for CUDA 11.x are no longer published, potentially breaking existing setups.

fix

Update CUDA toolkit, drivers, and related dependencies to version 12.x or higher when utilizing GPU execution providers.

affects: >=1.22.0

breakingThe minimum supported Windows version for ONNX Runtime has been raised to 10.0.19041 (Windows 10, version 20H1).

fix

Ensure target Windows machines are running OS Build 10.0.19041 or newer to avoid compatibility issues.

affects: >=1.22.0

gotchaThis `onnxruntime-common` package is designed as a shared API layer and is not intended for direct use. End-user applications should install and depend on platform-specific packages.

fix

For Node.js, install `onnxruntime-node`. For browsers, use `onnxruntime-web`. For React Native, use `onnxruntime-react-native`. Import core functionality from these specific packages.

affects: all

breakingCritical security vulnerabilities, including heap out-of-bounds read/write issues in `GatherCopyData` and `RoiAlign`, were fixed in version 1.24.3.

fix

Immediately upgrade to `onnxruntime-common@1.24.3` or a newer version to apply essential security patches and prevent potential exploits.

affects: 1.24.0 - 1.24.2

Errors

Common errors & fixes

Module not found: Can't resolve 'onnxruntime-common' in '...' or similar import errors

Attempting to directly import from `onnxruntime-common` without having it installed, or more commonly, trying to use it as a primary entry point for ONNX Runtime functionality.

fix

Install the correct platform-specific ONNX Runtime package (e.g., `npm install onnxruntime-node`) and adjust your imports to use that package directly (e.g., `import * as ort from 'onnxruntime-node';`).

TypeError: ort.InferenceSession.create is not a function

Attempting to call static methods like `create` directly on the `InferenceSession` symbol imported from `onnxruntime-common`. The common package often defines interfaces or abstract classes, not concrete implementations with static factory methods.

fix

Ensure you are importing and calling `create` from the platform-specific package's `InferenceSession` implementation (e.g., `import * as ort from 'onnxruntime-node'; const session = await ort.InferenceSession.create('model.onnx');`).

Error: ONNX Runtime requires an execution provider. Please ensure you have enabled at least one.

While `onnxruntime-common` doesn't directly cause this, it's a common error that propagates from platform-specific packages if no valid execution provider (e.g., WASM, WebGPU, CPU, CUDA) is found or explicitly configured during session creation.

fix

When creating an `InferenceSession`, pass `sessionOptions` to explicitly define execution providers, for example: `{ executionProviders: ['webgpu', 'wasm'] }` for web or `{ executionProviders: ['cuda', 'cpu'] }` for Node.js.

Upgrade

Version history

1.24.3latest on npm

Audit

Dependencies

No dependency data recorded yet.

Agent activity

8 hits · last 30 days

node

Resources

githubhttps://github.com/Microsoft/onnxruntime ↗

packagehttps://www.npmjs.com/package/onnxruntime-common ↗

homepagehttps://onnxruntime.ai ↗