Your Self-Hosted LLM Needs to Say No - Harshul Jain & Parv Khatri, Audible & SAP
AI Engineer talk on making self-hosted LLMs refuse appropriately in production; practical serving and guardrail lessons.
More in Infra
1:34:10InfraLocal AI 301: Quantization
Hugging Facequantizationcourse
7:12InfraYour KV Cache Can Spot Attacks on Your AI Agents - Ari Azarafrooz, Intrinsec AI
KV cacheagent securitytalk
4:51InfraNVIDIA Dynamo in 5 Minutes: The Frontend, a Drop-In OpenAI API
NVIDIA Dynamoinferencetutorial
