3 | @PaloAltoNtwks
Serving Small Language Models with SGLang for Malicious Traffic Detection
Zhemin Su & Matthew Schulz on low-latency, high-throughput SLM serving for real-time threat detection.
Palo Alto Networks explains serving small language models with SGLang for threat detection
AIPalo Alto Networks authors Zhemin Su and Matthew Schulz describe serving small language models with SGLang for malicious traffic detection. The post focuses on low-latency, high-throughput serving for real-time threat detection.
@lmsysorg
Part of a thread · earlier post