Finetune Llama 3.1 on Your Infra
Operational guide to finetune Llama 3.1, with everything packaged in a simple SkyPilot YAML.
Posts
AI on Kubernetes Without the Pain
SkyPilot 0.6: Managed Jobs API, SkyServe on Kubernetes, Spot + On-demand mixing, Paperspace support
Introducing SkyServe: 50% Cheaper AI Serving on Any Cloud with High Availability
SkyServe: A simple, cost-efficient, multi-region/cloud library for serving GenAI models.
Scaling Mixtral LLM Serving with High GPU Availability and Cost Efficiency
A tutorial for serving Mixtral 8x7B model with SkyPilot and SkyServe.