2026
AsyncSpade: Efficient Test-Time Scaling with Asynchronous Sparse Decoding
ICML 2026poster
Test-time scaling (TTS) can boost LLM reasoning through long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware sparse decoding methods can achieve state-of-the-art performance under constrained FLOP budget, but are mainly constr…