3 papers
cs.CL2026
SSSD: Simply-Scalable Speculative Decoding
Michele Marzollo, Jiawei Zhuang, Niklas Roemer +3
Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in pro…
cs.LG2026
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks
Lorenz K. Muller, Philippe Bich, Chiara Boretti +3
Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows…
cs.LG2026
SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights
Lorenz K. Müller, Philippe Bich, Jiawei Zhuang +3
Post-training quantization has emerged as the most widely used strategy for deploying large language models at low precision. Still, current methods show perplexity degradation at…