llama.cpp

76a88492 - ggml : add CLBlast q5_0, q5_1, q8_0 dequant kernels (#1225)

ggml : add CLBlast q5_0, q5_1, q8_0 dequant kernels (#1225) * Implement q5_0, q5_1 and q8_0 * Work around q5_0 OpenCL issue * Fix q8_0 dequant kernel * Move cl kernels into ggml-opencl.c * Use two memcpy calls for q5_0 buffer transfer