feat: TQ4_1S weight compression (Metal only, needs CUDA port) by TheTom · Pull Request #45 · TheTom/llama-cpp-turboquant

Summary TQ3_1S (3-bit, 4.0 BPW) and TQ4_1S (4-bit, 5.0 BPW) weight quantization using WHT rotation + Lloyd-Max centroids V2.1 fused Metal kernel: zero threadgroup memory, cooperative SIMD rotation...