Nexa AI SDK for Enterprise
Project description
Nexa-SDK-Enterprise
Enterprise SDK for Nexa AI's model serving on edge devices.
Python Package Installation
We have released pre-built wheels for various Python versions, platforms, and backends for convenient installation on our index page.
CPU Installation
pip install nexa-enterprise --prefer-binary --index-url https://nexaai.github.io/nexa-sdk-enterprise/whl/cpu --extra-index-url https://pypi.org/simple --no-cache-dir
GPU Installation (Vulkan)
To install with Vulkan support, make sure you have Vulkan SDK 1.3.261.1 or later installed.
For Windows PowerShell:
$env:CMAKE_ARGS="-DGGML_VULKAN=on"; pip install nexa-enterprise --prefer-binary --index-url https://nexaai.github.io/nexa-sdk-enterprise/whl/vulkan --extra-index-url https://pypi.org/simple --no-cache-dir
For Windows Command Prompt:
set CMAKE_ARGS="-DGGML_VULKAN=on" & pip install nexa-enterprise --prefer-binary --index-url https://nexaai.github.io/nexa-sdk-enterprise/whl/vulkan --extra-index-url https://pypi.org/simple --no-cache-dir
For Windows Git Bash:
CMAKE_ARGS="-DGGML_VULKAN=on" pip install nexa-enterprise --prefer-binary --index-url https://nexaai.github.io/nexa-sdk-enterprise/whl/vulkan --extra-index-url https://pypi.org/simple --no-cache-dir
Local Build (You may need to acquire access to this private repo first.)
How to clone this repo:
git clone --recursive https://github.com/NexaAI/nexa-sdk-enterprise
If you forget to use --recursive, you can use below command to add submodule:
git submodule update --init --recursive
Then you can build and install the package:
pip install -e .
Unit Tests
python -m tests.test_text_generation
python -m tests.test_disk_kv_cache
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nexa_enterprise-0.0.9.8.tar.gz
(34.2 MB
view details)
File details
Details for the file nexa_enterprise-0.0.9.8.tar.gz.
File metadata
- Download URL: nexa_enterprise-0.0.9.8.tar.gz
- Upload date:
- Size: 34.2 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9a21808acc505e65d3b64d1b1c5f2bb331f3ad3124b63eb38f6fbec20350c72d
|
|
| MD5 |
348ce8de126cd7bf8e25d7b1265a6fa8
|
|
| BLAKE2b-256 |
11a9cde1f3cf8927282bec10260c45a68f3def18662cabafc6ff13ed0ea3a4a1
|