llm-cpp-inference
PublicC++ wrapper for LLM Inference using libcurl – A C++ implementation for interacting with locally served language models (LLMs) via HTTP requests. Powered by ollama and libcurl, the project demonstrates LLM inference on local setups without relying on external APIs.
Creat：2024-10-14T07:29:35
Update：2024-11-25T10:23:48
3
Stars
0
Stars Increase