frink-quant
Quantized weight formats and fused dequant kernels for Frink.
Block layouts (Q4_K, Q8_0, …), repacking, and CPU fused dequant+dot used by
frink-core and the Metal/CUDA backends.
Quantized weight formats and fused dequant kernels for Frink.
Block layouts (Q4_K, Q8_0, …), repacking, and CPU fused dequant+dot used by
frink-core and the Metal/CUDA backends.