Goal / Module Layout / Key Design Decisions (multi-head layout via reshape+transpose_3d01+split/merge_heads, embedding gather/scatter-add, x@W convention, causal mask, params API, overfit methodology) / 验证方法 with the dash5 results (grad-checks, overfit 2.82->0.004, PyTorch parity). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>