deharoalexandre-cyber/EIE
Local GGUF inference for one or several models; Android JNI components and experimental Gemma expert-weight streaming with published local measurements.
GitHub repository with 5 stars and 2 forks.
Language: C++
Topics: apache-2, cuda, gguf, inference, llama-cpp, llm, multi-model, openai-api, rocm, turboquant