Glossary · Inference & serving

FlashAttention

A GPU-optimized attention algorithm that avoids materializing the full attention matrix in memory, making long-context inference and training much faster.

Related terms

• KV cache
• Ollama
• PagedAttention
• SGLang
• autoscaling (inference)
• batch API

Vynaris is an inference gateway that routes each request to the cheapest right-sized model and shows the receipt. Get an API key or read the docs.