Glossary · Inference & serving

autoscaling (inference)

Automatically adding or removing model-serving replicas based on real-time request load.

Related terms

• FlashAttention
• KV cache
• Ollama
• PagedAttention
• SGLang
• 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.