1. Georgi Gerganov
https://github.com/ggerganov
https://ggerganov.com/
ggml-org
https://github.com/ggml-org
GGML – AI at the edge
https://ggml.ai/
ggml.ai is a company founded by Georgi Gerganov to support the development of ggml.
ggml is a tensor library for machine learning to enable large models and high performance on commodity hardware. It is used by llama.cpp and whisper.cpp.
1.1. Projects
whisper.cpp
https://github.com/ggerganov/whisper.cpp
High-performance inference of OpenAI’s Whisper automatic speech recognition model
The project provides a high-quality speech-to-text solution that runs on Mac, Windows, Linux, iOS, Android, Raspberry Pi, and Web
llama.cpp
https://github.com/ggerganov/llama.cpp
Inference of Meta’s LLaMA model (and others) in pure C/C++
The project provides efficient inference across a wide range of hardware and serves as the foundation for numerous LLM-based applications
2. ggml
https://github.com/ggerganov/ggml
Tensor library for machine learning
Some of the development is currently happening in the llama.cpp and whisper.cpp repos.
sync : llama.cpp
sync : whisper.cpp

3. llama.cpp
https://github.com/ggerganov/llama.cpp
Inference of Meta’s LLaMA model (and others) in pure C/C++
The llama.cpp project is the main playground for developing new features for the ggml library.
sync : ggml

4. whisper.cpp
https://github.com/ggerganov/whisper.cpp
High-performance inference of OpenAI’s Whisper automatic speech recognition (ASR) model.
The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library.
sync : ggml
sync : ggml + llama.cpp
sync : ggml and llama.cpp

References
[1] Yongqiang Cheng, https://yongqiang.blog.csdn.net/
[2] Introduction to ggml, https://huggingface.co/blog/introduction-to-ggml
文章来源于互联网:Georgi Gerganov – ggml – llama.cpp – whisper.cpp
相关推荐: AI绘画工具Stable Diffusion中的常用术语解析,一文搞懂关键术语,让你事半功倍!
对于很多初学者来说,会对Stable Diffusion中的很多术语感到困惑,当然你不是唯一的那个。 ===================================================== 在这篇文章中,我将会讲解几乎所有你在Stable …
5bei.cn大模型教程网











