Attention on Sandeep Kumarhttps://sandeep007734.github.io/tags/attention/Recent content in Attention on Sandeep KumarHugoen-usWed, 12 Aug 2026 00:00:00 +0530The KV Cache: Sizing It, and the Attention Variants That Shrink Ithttps://sandeep007734.github.io/posts/kv_cache_and_gqa/Wed, 12 Aug 2026 00:00:00 +0530https://sandeep007734.github.io/posts/kv_cache_and_gqa/Why decoding needs a KV cache, the exact formula for its size, why it makes decode memory-bound, and how multi-query, grouped-query, and latent attention change the constant in that formula.