grouped-query-attention

Tag

Cards List
#grouped-query-attention

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

Hugging Face Daily Papers · 2026-06-18 Cached

Grouped Query Experts (GQE) improves Transformer efficiency by applying a mixture-of-experts layer on top of grouped-query attention, selectively activating query heads per token while keeping key-value cache benefits, matching baseline accuracy with half the query-head compute at 250M parameter scale.

0 favorites 0 likes
#grouped-query-attention

MiniMax Sparse Attention

Hugging Face Daily Papers · 2026-06-11 Cached

MiniMax Sparse Attention introduces a blockwise sparse attention mechanism that achieves significant speedups for ultra-long-context LLMs, reducing per-token attention compute by 28.4x at 1M context with wall-clock speedups of 14.2x for prefill and 7.6x for decoding on H800 GPUs. The method is accompanied by an open-source inference kernel and a publicly released multimodal model.

0 favorites 0 likes
#grouped-query-attention

GQA-{\mu}P: The maximal parameterization update for grouped query attention

arXiv cs.LG · 2026-05-18 Cached

This paper extends the maximal update parameterization (μP) framework to grouped-query attention (GQA), deriving scaling laws for hyperparameter transfer across model architectures. It introduces spectral norm conditions for feature learning and addresses issues with low-rank weight matrices in GQA.

0 favorites 0 likes
#grouped-query-attention

Architecture, Not Scale: Circuit Localization in Large Language Models

arXiv cs.CL · 2026-05-12 Cached

This paper challenges the assumption that mechanistic interpretability becomes harder as models scale, showing that architecture (specifically Grouped Query Attention vs. Multi-Head Attention) matters more than parameter count for circuit localization and stability.

0 favorites 0 likes
← Back to home

Submit Feedback