//! RTX Training Stack - Complete training and optimization
//!
//! Everything needed for state-of-the-art ML training:
//! - Advanced transformer architectures
//! - Distributed training across multiple nodes
//! - Flash Attention for memory efficiency  
//! - Reinforcement Learning with Human Feedback (RLHF)
//! - Model compression and optimization

#![forbid(unsafe_code)]

// Core
pub use rtx_autograd as autograd;
pub use rtx_tensor as tensor;

// Training
pub use rtx_compress as compress;
pub use rtx_distributed as distributed;
pub use rtx_flash_attention as flash_attention;
pub use rtx_rl as rl;
pub use rtx_transformers as transformers;

/// Training essentials
pub mod prelude {
    pub use rtx_tensor::{Device, Tensor};
    // Use the correct exports from rtx_transformers
    pub use rtx_distributed::distributed_transformer_trainer::DistributedTransformerTrainer;
    pub use rtx_flash_attention::FlashAttention;
    pub use rtx_transformers::architectures::{TransformerArchitecture, TransformerConfig};
    // Use the correct exports from rtx_rl
    pub use rtx_rl::actor_learner::ActorLearner;
}