pub fn execute_mtp_standalone(
plan: &ModelPlan,
weights: &ReferenceWeights,
token_ids: &[u32],
trunk_hidden: &[f32],
) -> Result<Vec<ReferenceMtpOutput>, ReferenceError>Expand description
Execute ONLY the MTP draft arm on CALLER-PROVIDED trunk wide states — the
real-checkpoint draft-parity instrument (mtp-spec lane): the full-trunk host
reference cannot hold the 360 GB artifact, but the MTP block’s rows fit host f32,
so the engine’s captured trunk wide state feeds this host twin and the draft
programs are compared row for row. trunk_hidden is [tokens, streams*hidden]
(gated-residual plans) or [tokens, hidden]; row i seeds token_ids[i] — the same
pairing execute uses internally.