pub mod config;
pub mod decode_graph;
pub mod gpt2;
pub mod kv_cache;
pub mod loader;
pub mod paged_kv_cache;
pub mod qwen3;
pub mod sampling;

pub use config::ModelConfig;
pub use decode_graph::{DecodeGraphState, LayerWeightPtrs};
pub use gpt2::{GPT2, KVCache};
pub use kv_cache::GpuKVCache;
pub use paged_kv_cache::{BlockAllocator, Location, PagedKVCache, BLOCK_SIZE};
pub use qwen3::Qwen3;
pub use sampling::{SamplingParams, sample};

/// Initialize GPU kernel hooks. Called automatically by model constructors,
/// but safe to call multiple times (idempotent via OnceLock).
pub fn init_kernels() {
    xserv_kernels::init();
}