#llm #build #cpp #llama #binary #server #compile

llama_cpp_low

small server binary compile build from llama.cpp

17 releases

0.3.14 Sep 6, 2024
0.3.13 Jul 12, 2024
0.3.7 Jun 19, 2024
0.3.5 May 9, 2024

#42 in #llama


Used in llm-daemon

MIT license

8MB
163K SLoC

C++ 85K SLoC // 0.1% comments C 35K SLoC // 0.1% comments Python 16K SLoC // 0.1% comments CUDA 7.5K SLoC // 0.0% comments Metal Shading Language 5K SLoC // 0.0% comments GLSL 3.5K SLoC // 0.0% comments Objective-C 3K SLoC // 0.0% comments Shell 2.5K SLoC // 0.2% comments JavaScript 2.5K SLoC // 0.2% comments Swift 1K SLoC // 0.0% comments Kotlin 694 SLoC // 0.1% comments Gherkin (Cucumber) 560 SLoC // 0.1% comments Vim Script 135 SLoC // 0.1% comments RPM Specfile 109 SLoC // 0.2% comments Batch 78 SLoC // 0.2% comments Prolog 36 SLoC Rust 27 SLoC INI 7 SLoC

Contains (JAR file, 60KB) gradle-wrapper.jar

llama-cpp-low

Script to build llama.cpp server binary using cargo

Wait, are you sober?

I just wanted to have the daemon to run the LLM with minimal external dependency...

No runtime deps