InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale.

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

Multiple UAV Flight Control Signals Extraction Based on Optimized Local Maximum with FPGA Implementation

Abstract: The illegal operation of unmanned aerial vehicles (UAVs) has raised significant public safety concerns, especially the challenge of identifying UAV operators in complex electromagnetic ...
IEEE

Parallel Scan on Ascend AI Accelerators

Abstract: We design and implement parallel prefix sum (scan) algorithms using Ascend AI accelerators. Ascend accelerators feature specialized computing units—the cube units for efficient matrix ...