3 papers
cs.CL2026
Revisiting Judge Decoding from First Principles via Training-Free Distributional Divergence
Shengyin Sun, Yiming Li, Renxi Liu +5
Judge Decoding accelerates LLM inference by relaxing the strict verification of Speculative Decoding, yet it typically relies on expensive and noisy supervision. In this work, we r…
cs.CL2025
Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
Shengyin Sun, Yiming Li, Xing Li +8
Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources durin…
cs.LG2025
KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
Xing Li, Zeyu Xing, Yiming Li +6
KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness.…