Npu Python Packages

optimum-rbln

⚡ A seamless integration of HuggingFace Transformers & Diffusers with RBLN SDK for efficient inference on RBLN NPUs.

device-smi

Self-contained Python lib with zero-dependencies that give you a unified device properties for gpu, cpu, and npu. No more calling separate tools such as nvidia-smi or /proc/cpuinfo and parsing it yourself.

uc-manager

Persist and reuse KV Cache to speedup your LLM.

mblt-tracker

A lightweight Python library for tracking hardware metrics (Power, Utilization, Memory) across CPU, GPU, and NPU.

torch-rechub

A Lighting Pytorch Framework for Recommendation Models, Easy-to-use and Easy-to-extend.

rockchip-stats

Interactive system-monitor and process viewer for Rockchip SoC devices [RK3588, RK3588S, RK3568, RK3566, RK3399]

lemonade-python-sdk

A clean interface for interacting with the Lemonade LLM server

rk-transformers

Export and Run Hugging Face Transformers Models on Rockchip NPUs

ascend-nputop

An interactive Ascend-NPU process viewer.

maixtool

C/C++ development kit for Sipeed Maix ecosystem boards

rknn-inspect

A tool for inspecting RKNN models

nexil

A better way to run LLMs locally on Intel hardware (NPU or CPU) with a single command.

jllm

Running Large Language Model easily, faster and low-cost.

vimin-core

Source-available local AI inference orchestration — broadcast dispatch and multi-step pipelines across up to 10 nodes

pai-sdk

Reserved for PAI-OS SDK

maixcdk-example

C/C++ development kit for Sipeed Maix ecosystem boards

maixcdk

C/C++ development kit for Sipeed Maix ecosystem boards