Struct MockEngine 

pub struct MockEngine { /* private fields */ }

A mock engine implementation for Milestone A.

Uses a simple whitespace tokenizer and greedy sampler to demonstrate the “narrow waist” API without requiring a real model or MLX backend.

Implementations

impl MockEngine

pub fn new() -> Self

Trait Implementations

impl Default for MockEngine

fn default() -> Self

Returns the “default value” for a type.

impl LlamaEngine for MockEngine

fn load_model(&self, _spec: &ModelSpec) -> Result<ModelHandle>

Load a model from disk given a specification.

fn tokenize(&self, text: &str) -> Result<Vec<TokenId>>

Convert text into a sequence of token IDs.

fn detokenize(&self, tokens: &[TokenId]) -> Result<String>

Convert token IDs back into text.

fn prefill( &self, _session: &mut Session, tokens: &[TokenId], ) -> Result<PrefillResult>

Run the prefill phase: process prompt tokens and populate the KV cache.

fn decode(&self, _session: &mut Session) -> Result<DecodeResult>

Run the decode phase: produce the next token from the model.

fn embed(&self, texts: &[&str]) -> Result<Vec<Vec<f32>>>

Generate embeddings for a batch of texts (for oxidizedRAG integration).