2 papers
cs.LG2026
QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
Zunhai Su, Yuxuan Sun, Jianchao Tan +5
Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memory still scales linearly with…
cs.LG2026
FluxBin: Flexible LUT-based Ultra-low-bit LLM Inference by Algorithm-Kernel Synergy
Qingyao Yang, Runming Yang, He Xiao +7
While binary quantization theoretically promises extreme compression and acceleration for Large Language Models (LLMs), existing research often overlooks the necessity of specializ…