pub fn hash_chunks(model: &str, tokens: &[u32]) -> Vec<[u8; 32]>Expand description
Walk a full token sequence and yield one digest per TOKENS_PER_CHUNK
rolling chunk. The last (partial) chunk is also emitted because it is
often the most cache-relevant.
Position-independent: equal token-windows at different positions
hash to the same digest. Use hash_seq_chunks when KV-cache reuse
requires positional fidelity.