- https://layerscale.ai/
- https://layerscale.ai/benchmarks
- Inference engine built for agents and streams. Data is processed the moment it arrives, not when you query.
- Cited numbers: 0.383ms flash query on a live 8k-token stream (p50); 2.818ms/token single-stream decode 128 in / 128 out (p50); 90,229.87 tok/s prefill on a 4,096-token prompt.
- Free version also available.
Connections
No outgoing connections.