pub fn glm52_forward_token(
weights: &Glm52DecoderWeights,
cfg: &Glm52DecoderConfig,
token_id: usize,
state: &mut Glm52DecodeState,
) -> Vec<f32>Expand description
One decode step across every layer. prev_top_k is reset to None
at the start of this function (per-token-forward-pass scope, see
glm_dsa::glm52_attn_forward_token’s doc comment) – it must not be
threaded in from a previous token.