Struct Llama32Runner 

pub struct Llama32Runner { /* private fields */ }

Implementations

impl Llama32Runner

pub fn builder() -> Llama32RunnerBuilder

pub fn config(&self) -> &Llama32Config

pub fn device(&self) -> Device

pub fn predict_logits(&mut self, prompt_ids: &[u32]) -> Result<Vec<f32>, Error>

Single prefill forward; returns last-position logits [vocab].

pub fn generate_packed( &mut self, prompt_ids: &[u32], n_new: usize, on_token: impl FnMut(u32), ) -> Result<Vec<u32>, Error>

pub fn generate( &mut self, prompt_ids: &[u32], n_new: usize, on_token: impl FnMut(u32), ) -> Result<Vec<u32>, Error>

Trait Implementations

impl LmRunner for Llama32Runner

fn family(&self) -> &'static str

Short family identifier ("qwen3", "llama32", "gemma").

fn vocab_size(&self) -> usize

LM head vocabulary size.

fn predict_logits(&mut self, prompt_ids: &[u32]) -> Result<Vec<f32>, Error>

Run prefill on prompt_ids and return last-token logits.

fn generate( &mut self, prompt_ids: &[u32], n_new: usize, on_token: &mut dyn FnMut(u32) -> bool, ) -> Result<Vec<u32>, Error>

Generate up to n_new tokens after prompt_ids using greedy (argmax) sampling. The default impl re-prefills on the full context each step — per-family runners should override with their cached decode fast path.

fn supports_multimodal(&self) -> bool

Whether this runner supports multimodal (image+text) generation.

fn generate_multimodal( &mut self, _prompt: &str, _rgb: &[u8], _img_w: usize, _img_h: usize, _tokenizer: Option<&Path>, _n_new: usize, _on_token: &mut dyn FnMut(u32) -> bool, ) -> Result<Vec<u32>, Error>

Multimodal generation: prefill with text where image markers are spliced with vision embeddings derived from rgb.