conftrace_

grouped-query attention

9 papers

Explore in graph

Also known as

GQA

Co-occurring keywords · papers mentioning both

large language model (4) inference efficiency (4) memory optimization (4) model compression (4) multi-query attention (3) kv cache (3) memory efficiency (3) efficient computing (3) key-value cache (2) model architecture (2)

Papers

Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA EMNLP 2025 Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025 KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding ACL 2025 Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization EMNLP 2025 MLKV: Multi-Layer Key-Value Heads for Memory Efficient Transformer Decoding NAACL 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases ICML 2024 Reducing Transformer Key-Value Cache Size with Cross-Layer Attention NeurIPS 2024 GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints EMNLP 2023