Module executor 

Model executor implementations

Re-exports

pub use bert_executor::BertModelExecutor;

pub use candle_executor::CandleModelExecutor;

pub use qwen2_executor::Qwen2ModelExecutor;

pub use qwen3_executor::Qwen3ModelExecutor;

pub use stub_executor::StubModelExecutor;

Modules

bert_executor

BERT Model Executor for embeddings

candle_executor

Llama model executor using our custom Llama implementation.

common

Common executor utilities — extracted from duplicated code across Qwen3, Qwen2, and Llama executors.

qwen2_executor

Qwen2 model executor using Candle

qwen3_executor

Qwen3 model executor using Candle

stub_executor

Stub model executor for MVP testing and development

tp_executor

Tensor-Parallel model executor.