BeeLlama.cpp is a performance-focused llama.cpp fork adding variance-normalized KV-cache quantization, precision tails, and low-bit cache types for faster local GGUF inference.
1195ggml,kv-cache,llama-cppBeeLlama.cpp is a performance-focused llama.cpp fork adding variance-normalized KV-cache quantization, precision tails, and low-bit cache types for faster local GGUF inference.