FAME-QP, a GPU-Accelerated Quadratic-Programming Solver, Announced
FAME-QP, a GPU-accelerated solver for dense quadratic programs in linear model predictive control, has been announced. It reportedly achieves reduced latency compared to competing GPU solvers while maintaining solution accuracy and control performance.
FAME-QP, a GPU-accelerated solver for dense quadratic programs arising in linear model predictive control, was presented in Hugging Face Papers. The solver combines constraint-dependent operator representations with fused single- and two-kernel iterations replayed through CUDA graphs, automatically selecting the execution configuration through device calibration and problem-specific timing.
FAME-QP probes a cached operator bank to select the initial penalty and updates operators lazily when problem matrices change. Numerical benchmarks and simulated humanoid and quadrotor control experiments demonstrate reduced latency relative to competing GPU solvers while maintaining solution accuracy and control performance, according to the researchers.
This item is a summary. The full, checkable version is at the original source:
Read the original at Hugging Face Papers ↗