2 papers
cs.AR2026
SPECTRA: Adaptive Execution of Speculative Decoding on a Runtime-Reconfigurable Tiled Architecture
Gabriele Tombesi, William Baisi, Je Yang +5
LLM inference on edge devices is constrained by computational and memory resources, making efficient autoregressive decoding challenging. Speculative decoding alleviates this bottl…
cs.AR2026
HSCO-Bench: An Agent-Driven End-to-End Hardware-Software Co-design Benchmark for Systems-on-Chip
Pei-Huan Tsai, Kuan-Lin Chiu, William Baisi +2
Large language models (LLMs) are adopted for software and hardware design, yet these domains are still evaluated separately. Software benchmarks typically assume fixed hardware tar…