{"slug": "grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction", "title": "Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction", "summary": "Researchers introduced Grouped Value Attention, a method that reduces the Transformer KV cache by reconstructing keys on demand rather than storing them at every decoding step. The technique builds on grouped-query attention (GQA), which already cuts cost by sharing key-value heads but still stores both a key and a value at each step; Grouped Value Attention instead stores only values and reconstructs keys as needed. The KV cache is a primary bottleneck for Transformer decoding because its memory footprint and cache-read traffic grow with sequence length.", "body_md": "The KV cache is a primary bottleneck for Transformer decoding: its memory footprint and cache-read traffic grow with sequence length. Grouped-query attention (GQA) reduces this cost by sharing key-value heads, but still stores both a key and a value at every step. We introduce Grouped Value Attentio", "url": "https://wpnews.pro/news/grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction", "canonical_source": "https://aiflash.com/news/119880/", "published_at": "2026-09-15 08:00:08+00:00", "updated_at": "2026-09-15 08:41:38.787339+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-infrastructure"], "entities": ["Grouped Value Attention", "grouped-query attention", "KV cache", "Transformer"], "alternates": {"html": "https://wpnews.pro/news/grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction", "markdown": "https://wpnews.pro/news/grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction.md", "text": "https://wpnews.pro/news/grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction.txt", "jsonld": "https://wpnews.pro/news/grouped-value-attention-efficient-kv-caching-via-on-demand-key-reconstruction.jsonld"}}