Nexa AI

All

13 repositories

nexa-sdk
Public
On device AI inference in minutes—now for MLX & GGUF, with Android, iOS and NPU backends coming soon.
go sdk transformers language-model vlm edge-computing on-device-ml on-device-ai llm stable-diffusion
Go
•
Apache License 2.0
•645•4.6k•7•0•Updated Aug 9, 2025Aug 9, 2025
llama.cpp-for-sdk
Public
C++
•
MIT License
•0•0•0•1•Updated Aug 8, 2025Aug 8, 2025
mlx-audio-for-sdk
Public
Python
•
MIT License
•0•0•0•0•Updated Aug 7, 2025Aug 7, 2025
nexa-sdk-v1
Public
Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
Python
•
Apache License 2.0
•0•0•0•0•Updated Aug 4, 2025Aug 4, 2025
dolomite-engine
Public
Dolomite Engine is a library for pretraining/finetuning LLMs
Python
•
Apache License 2.0
•20•1•0•0•Updated Apr 12, 2025Apr 12, 2025
nexa-sdk-enterprise
Public
Python
•0•0•0•0•Updated Mar 12, 2025Mar 12, 2025
llama.cpp-deprecated
Public
LLM inference in C/C++, with Nexa AI's support for audio language model and swift binding
C++
•
MIT License
•13k•2•0•0•Updated Mar 5, 2025Mar 5, 2025
benchmark-tasks
Public
Nexa AI benchmark tasks
Python
•1•1•0•0•Updated Feb 11, 2025Feb 11, 2025
stable-diffusion.cpp
Public
Fork of Stable Diffusion CPP
C++
•
MIT License
•406•0•0•0•Updated Feb 6, 2025Feb 6, 2025
bark.cpp
Public
Fork of Suno AI's Bark model in C/C++
C++
•
MIT License
•74•0•0•0•Updated Jan 24, 2025Jan 24, 2025
Awesome-LLMs-on-device
Public
Awesome LLMs on Device: A Comprehensive Survey
awesome awesome-list on-device llm
MIT License
•107•1.2k•1•1•Updated Jan 12, 2025Jan 12, 2025
Ocotpus-v2-demo
Public
Android ChatBot with Octopus v2 - Function Calling Demo
Java
•4•15•2•0•Updated Jul 30, 2024Jul 30, 2024
octopus-v4
Public
AI for all: Build the large graph of the language models
graph distributed-computing large-language-models
Python
•
Other
•21•272•3•0•Updated Jun 3, 2024Jun 3, 2024