cd/entity/H800 GPU· home› entities› H800 GPU
grep -l @h800 gpu /news/*.json | wc -l → 1

H800 GPU

mentions 1 type Person feed RSS

// recent coverage 1 mentions

05:00
2026-06-22
dev.to
large-language-models

Sparse KV Caches Cut Attention Scaling

MiniMax introduced sparse key-value caches that reduce attention scaling from quadratic to near-linear, enabling practical multi-hundred-kilobyte context windows on a single GPU. The method cuts per-t…

// co-occurs with top 3 entities
MiniMax 1 Grouped Query Attention 1 MSA 1
// topics top 5 topics
large language models 1 ai research 1 ai infrastructure 1 machine learning 1 neural networks 1