pub fn ssm_rowwise_w_bf16_layer_bytes(config: &ModelConfig) -> usizeExpand description
2026-09-25: BF16 bytes of one GDN layer’s row-wise copies: in_proj_qkvz
[ssm_qkvz_size, hidden] and out_proj [hidden, value_dim], the two
weights set_fp8_rowwise_prefill_weights installs, with
value_dim = linear_num_value_heads * linear_value_head_dim. At the
Qwen3.8-27B shapes of buffers/tests.rs (hidden 5120, 16x128 key heads,
48x128 value heads) that is 167772160 + 62914560 B.