RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention
arXiv:2610.20686v1 Announce Type: new Abstract: Multi-head latent attention (MLA) compresses the content of a key-value cache into a shared latent per token, making low-bit storage attractive for long-context inference. At two bits, errors in this representation perturb both attention matching and…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv cs.LG
RoLaQ: Joint Rotation and Range Calibration for 2-Bit KV Caches in Multi-Head Latent Attention