arXiv cs.AI
· Papers
GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding
arXiv:2605.15250v3 Announce Type: replace-cross Abstract: Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the H100 roofline almost perfectly. Its trained weights, however, expose only one decoding path - an absorbed MQA form