Researchers baked 3x inference speedups directly into LLM weights — without speculative decoding

Researchers from the University of Maryland, Lawrence Livermore, Columbia and TogetherAI have developed a training technique that triples LLM inference speed without auxiliary models or infrastructure ...
IEEE

Two-bit multi-level spin orbit torque MRAM with the fully one-step write operation

Abstract: As an emerging non-volatile memory technology, the spin orbit torque magnetic random access memory (SOT-MRAM) has attracted intensive research interest due to its advanced performance.