SDK Installation

After purchasing the SDK, you will receive the installer and dependency library files.

Install SDK

Install the SDK and its required components:

Note

The codemeter_api package is provided in the download package. Install it from the bundle folder.
FlashAttention is optionally supported to accelerate inference. However, due to its build and CUDA requirements, it may not be compatible with all environments, even when the libraries listed in the required dependencies are installed. If your environment supports it, you can install FlashAttention using the provided command. A compatibility-tested prebuilt version is also included in the bundle for convenience. (See flash-attention-prebuild-wheels for reference.)

Ubuntu

pip install wave_8b_<high/mid>-<version>-py3-none-any.whl
pip install flash-attn --no-build-isolation
pip install ./codemeter_api-8.40.500-py3-none-any.whl

Install Dependency Libraries

Create a requirements.txt file with the following dependencies:

Third-Party Libraries

Certain features in this SDK depend on libraries maintained by independent third parties. While the SDK has been tested with specific versions for compatibility, ongoing updates and security maintenance are handled by each library's own maintainers. We recommend reviewing the official documentation for these libraries and installing secure, supported versions that meet your project's requirements.

accelerate==1.10.1
av==15.1.0
decord==0.6.0
imageio==2.37.0
opencv-python==4.12.0.88
timm==1.0.19
transformers==4.56.1
torch==2.9.1
torchvision==0.24.1
wheel==0.46.2
vllm==0.14.1
scipy==1.15.3

Install all dependencies from the file:

Ubuntu

pip install -r requirements.txt

Verify Installation

Test the installation by importing the SDK:

Python

from woven.vision.ai.wave_8b.vllm_client import VLLMClient
client = VLLMClient()

On first import, you will be prompted to acknowledge the End User License Agreement (EULA). This confirmation is required only once.

← Previous: License Activation

Next: API Reference →