llama.cpp

77a73403 - ggml : add new Q4_2 quantization (ARM only) (#1046)

ggml : add new Q4_2 quantization (ARM only) (#1046) * ggml : Q4_2 ARM * ggml : add ggml_is_quantized() * llama : update llama_type_name() with Q4_2 entry * ggml : speed-up q4_2 - 4 threads: ~100ms -> ~90ms - 8 threads: ~55ms -> ~50ms * ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32