fn prefill_prompt(
gpu: &mut Gpu<'_>,
cpu: Option<&CpuModel<'_>>,
cpu_state: Option<&mut State>,
ids: &[u32],
n_draft: usize,
resume: Option<PrefillResume>,
) -> Result<PrefillResume>Expand description
Fill the trunk and draft caches, then return the next token and draft chain.