Discussed On
Episodes
The a16z Show · Jan 22, 2026
Inferact: Building the Infrastructure That Runs Modern AI
AI Inference OptimizationOpen Source AI InfrastructureGPU Memory ManagementDistributed Systems ArchitectureLarge Language Model Serving
View AnalysisAI + a16z · Jan 22, 2026
Inferact: Building the Infrastructure That Runs Modern AI
Open source AI infrastructureGPU memory managementDynamic request schedulingPage attention algorithmsModel serving architecture
View Analysis