Registry / ai-ml / onnxruntime-directml

onnxruntime-directml

library1.24.4pypypiunverified

ONNX Runtime with DirectML execution provider for hardware-accelerated ML inference on Windows devices with DirectX 12 compatible GPUs. Version 1.24.4 requires Python >=3.11 and is maintained by Microsoft. Release cadence follows ONNX Runtime releases.

ai-ml

pip install onnxruntime-directml

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · ONNXRUNTIME-DIRECT

onnxruntime-directml

ai-mlpythonv1.24.4

Install

—

Import

—

Disk

—

Pass rate

0/ 10

Env Coverage0 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v? · pip 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

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

build_error

Code

Verified usage

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

InferenceSession

✓ from onnxruntime import InferenceSession

✗ from onnxruntime_directml import InferenceSession

Onnxruntime-directml does not expose its own InferenceSession; it uses the standard onnxruntime session. DirectML is enabled via session options.

SessionOptions

✓ from onnxruntime import SessionOptions

✗ import onnxruntime_directml

SessionOptions is in the onnxruntime package, not a separate directml package.

Basic inference using DirectML provider. Ensure model.onnx exists and is compatible.

import onnxruntime from onnxruntime import InferenceSession, SessionOptions # Enable DirectML execution provider options = SessionOptions() options.enable_training = False providers = ['DmlExecutionProvider', 'CPUExecutionProvider'] session = InferenceSession('model.onnx', options, providers=providers) # Run inference import numpy as np input_name = session.get_inputs()[0].name result = session.run(None, {input_name: np.random.randn(1, 3, 224, 224).astype(np.float32)})

Debug

Known issues

breakingPython 3.11 minimum required as of version 1.24.x. Older Python versions are unsupported.

fix

Upgrade Python to 3.11 or later, or use an older onnxruntime-directml version (but note older versions may lack features).

affects: >=1.24.0

gotchaDirectML execution provider requires Windows 10/11 with DirectX 12 GPU. It will not work on Linux or macOS. Trying to use DmlExecutionProvider on unsupported OS raises an error.

fix

Check platform before using DirectML: import sys; if not sys.platform.startswith('win'): raise RuntimeError('DirectML requires Windows').

affects: all

deprecatedUsing Oracle JDK is deprecated; only Liberica JDK is fully supported. The default JDK download in some documentation points to Oracle, which may cause compatibility issues.

fix

Use Liberica JDK 8 or 11 as the Java runtime for QuickSight.

affects: all

gotchaManually specifying the execution provider order can cause performance degradation if CPU provider is placed before DirectML. Setting providers list correctly is essential.

fix

Always place DirectML provider first: providers=['DmlExecutionProvider', 'CPUExecutionProvider'].

affects: all

Upgrade

Version history

1.24.4latest on PyPI · released Mar 17, 2026

Audit

Dependencies

numpyrequiredRequired for tensor operations in ONNX Runtime.

protobufrequiredUsed for serializing ONNX models.

sympyoptionalRequired for shape inference in some operators.

Agent activity

2 hits · last 30 days

node

Resources

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

packagehttps://pypi.org/project/onnxruntime-directml/ ↗

homepagehttps://onnxruntime.ai ↗