Pulse
0
Velocity
Stars
0
Efficient C++ implementation for running large language models locally.
Optimized C++ inference for DeepSeek LLM models with llama.cpp.
Run advanced DeepSeek LLMs locally with high performance via C++.
Why Trending
Fast, local LLM inference for DeepSeek models in C++.
Target Audience
Developers wanting to run LLMs on their own hardware.
Similar Projects