pub fn qwen38_tensors(cfg: &Qwen38Cfg) -> Vec<TensorLine>Expand description
Every tensor the authored forward declares — read from gen_qwen38_lg’s own output and classified by
the manifests it returns (Q8_0 matrices vs f32 tensors; the hidden state is the one undeclared-in-the-
manifests activation) — plus the embedding table the decode step gathers its input row from.