Local LLM Inference Engine & Multi-Model API by Aldian Fazrihady Local LLM Inference Engine & Multi-Model API by Aldian Fazrihady

Local LLM Inference Engine & Multi-Model API

Portfolio project
Aldian Fazrihady
An LLM chatbot that can installed on a local machine and accessed via the command line or network. https://github.com/aldian/llm-chatbot

0 likes · 35 views · Aug 22, 2024

High-throughput local LLM inference API supporting quantized weights (Mistral/LLaMA), streaming tokens, and OpenAI-compatible endpoints.

Tags