embedl-hub 2026.5.1

The official Embedl Hub Python client library.

Embedl Hub Python library

Optimize and deploy your model on any edge device with the Embedl Hub Python library:

• Compile your model for execution on CPU, GPU, NPU or other AI accelerators using ONNX Runtime, TensorRT, or TFLite backends.
• Profile your model's latency and memory usage on real edge devices in the cloud.
• Invoke your compiled model to run inference with real input data.

The library logs your metrics, parameters, and results on the Embedl Hub website, allowing you to inspect, compare, and reproduce your results.

For comprehensive getting started guides and API reference, visit the Embedl Hub documentation.

Create a free Embedl Hub account to get started.

Installation

embedl-hub requires Python 3.10 or newer.

The base install gives you experiment tracking, the CLI shell (auth, init, log, list-devices), and the Python tracking API — without pulling in any backend execution toolchain:

pip install embedl-hub

To use the bundled compile, profile, and invoke components (Embedl's ready-made wrappers for TFLite, ONNX Runtime, and TensorRT), install one or more toolchain extras:

Workflow	Install command
TFLite (local + QAI Hub + device cloud)	pip install 'embedl-hub[tflite]'
ONNX Runtime (QAI Hub + embedl-ORT)	pip install 'embedl-hub[onnxruntime]'
TensorRT (trtexec over SSH)	pip install 'embedl-hub[tensorrt]'
Everything	pip install 'embedl-hub[all]'

Linux aarch64 installs of [tflite] skip the onnx2tf-based local conversion path and the ai-edge-* quantization deps because the upstream TensorFlow package does not publish Linux aarch64 wheels. The QAI Hub TFLite provider still works.

Running a backend command without its extra installed prints a clear hint pointing at the right pip install command rather than a raw import traceback.

Usage

The embedl-hub library can be used in two ways:

CLI

The embedl-hub (or ehub) command provides an end-to-end workflow for compiling, profiling, and invoking models from the terminal:

Usage: embedl-hub [OPTIONS] COMMAND [ARGS]...

 embedl-hub end-to-end Edge-AI workflow CLI

╭─ Options ────────────────────────────────────────────────────────────────╮
│ --version      -V               Print embedl-hub version and exit.       │
│ --verbose      -v      INTEGER  Increase verbosity (-v, -vv, -vvv).      │
│ --help                          Show this message and exit.              │
╰──────────────────────────────────────────────────────────────────────────╯
╭─ Commands ───────────────────────────────────────────────────────────────╮
│ auth           Store the API key for embedl-hub CLI.                     │
│ init           Configure persistent CLI context.                         │
│ show           Print the active project name and artifact directory.     │
│ compile        Compile a model for on-device deployment.                 │
│ profile        Profile a compiled model on a target device.              │
│ invoke         Run inference on a compiled model.                        │
│ log            Show runs created with this CLI tool.                     │
│ list-devices   List available devices.                                   │
╰──────────────────────────────────────────────────────────────────────────╯

Python API

For programmatic use, import from the embedl_hub package. The API provides compiler, profiler, and invoker components for each supported backend (ONNX Runtime, TensorRT, TFLite):

from embedl_hub.compile import OnnxRuntimeCompiler
from embedl_hub.profile import OnnxRuntimeProfiler
from embedl_hub.invoke import OnnxRuntimeInvoker

See the Embedl Hub documentation for detailed guides and examples.

License

Copyright (C) 2025, 2026 Embedl AB

This software is subject to the Embedl Hub Software License Agreement.