GenieX
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
- 8.5k
- Go
- BSD-3-Clause
- 2 d ago
qualcomm
At Qualcomm Technologies, Inc., we transform how the world connects, computes and communicates.
Built from qualcomm's public GitHub profile. Not on Take My Repo yet, so there are no posts or updates here.
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
Command-line tool for flashing firmware on Qualcomm-based devices via USB Emergency Download (EDL) mode
Hexagon-MLIR is a compiler toolchain for compiling and executing AI kernels and models on Qualcomm Hexagon Neural Processing Units (NPUs).
QAI AppBuilder is designed to help developers easily execute models on WoS and Linux platforms. It encapsulates the Qualcomm® AI Runtime SDK APIs into a set of simplified interfaces for running models on the NPU/HTP.
FastRPC is Qualcomm's userspace library that facilitates efficient remote procedure calls between the CPU and DSP for high-performance computing.
This library empowers users to seamlessly port pretrained models and checkpoints on the HuggingFace (HF) hub (developed using HF transformers library) into inference-ready formats that run efficiently on Qualcomm Cloud AIxx (AI100, AI200 and so on) accelerators.
Qualcomm Cloud AI SDK (Platform and Apps) enable high performance deep learning inference on Qualcomm Cloud AI platforms delivering high throughput and low latency across Computer Vision, Object Detection, Natural Language Processing and Generative AI models.
Qualcomm kernel drivers provide logical representations of Qualcomm chipset-enabled mobile devices over USB connections. This repository includes source code, build scripts, and documentation for a set of device drivers designed for Qualcomm hardware platforms. The drivers support both Windows and Linux environments.
PatchWise automates patch review and static analysis for the Linux kernel, streamlining upstream contributions and ensuring code quality.
QCNode is Qualcomm's next-generation ADAS Hardware Abstraction Layer (HAL). It provides a set of user-friendly APIs that abstract the complexities of interacting with Qualcomm’s ADAS hardware accelerators. It simplifies the development of perception and computer vision apps by offering modular components and utilities tailored for ADAS use cases.