EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends Paper • 2610.24648 • Published 15 days ago • 16
MetaKernelBench: Measuring GPU Kernel Knowledge Transfer Beyond Code Paper • 2610.05014 • Published 28 days ago • 24
SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference Paper • 2610.12327 • Published 24 days ago • 34