Struct EmbedOverlay 

pub struct EmbedOverlay {
    pub rows: CudaSlice<f32>,
    pub spans: Vec<(usize, usize, usize)>,
}

Mixed-embedding prime overlay: image embeddings that replace <|image_pad|> token embeddings at prompt-relative positions during prime_cache_overlaid. rows holds all images’ merger outputs concatenated ([total_rows, n_embd]); each span is (prompt_pos, row_off, n_rows) — rows [row_off, row_off+n_rows) land at prompt positions [prompt_pos, prompt_pos+n_rows). Spans must not overlap.

Fields

rows: CudaSlice<f32>

spans: Vec<(usize, usize, usize)>

Implementations

impl EmbedOverlay

pub fn window(&self, off: usize, len: usize) -> Option<EmbedOverlay>

Sub-window for a prime call covering prompt-relative [off, off+len): spans clipped and rebased so the callee sees call-relative positions (the serve prefill tick primes a prompt across multiple prime_cache_overlaid calls). rows is an Arc clone, not a copy. None = no image rows in this window (caller may prime plain).