Inference Llama 2 in one file of pure C

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

MMseqs2: ultra fast and sensitive search and clustering suite

Foldseek enables fast and sensitive comparisons of large structure sets.

fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.

Makes llama.cpp easy to use.