Making LLMs Fast and Small: A Guide to Inference Optimization Research in 2026
Five approaches to making LLMs faster and cheaper — compression, diffusion decoding, architecture, KV cache, and sparse attention — explained with real numbers.
Llm-Compression
TriAttention Compresses KV Cache 10.7x — How Trigonometry Fixed Long-Context Reasoning
TriAttention uses pre-RoPE vector concentration and trigonometric scoring to compress KV cache 10.7x while matching full attention accuracy on reasoning tasks.