#State space models

SSM RAG Prefill Speedup Shatters Limits

SSM RAG prefill speedup slashes latency by 4500x on edge hardware, enabling interactive AI by pre-computing context.

Mamba 2 JAX: Hardware Agnostic SSMs

Mamba 2 JAX breaks hardware dependency for state-space models, achieving high performance on CPU, GPU, and TPU via XLA compilation without custom kernels.

Jamba 3B Model Unveiled AI21's Hybrid Architecture for Edge AI