Jeriel’sTechnology RadarMain Site

cast.ai

Cast AI LLM Autoscaler

A service for adjusting language-model serving capacity to demand.

https://cast.ai/lp/llm-autoscaler

About This Resource

A service for adjusting language-model serving capacity to demand. It focuses on scaling and routing inference workloads to balance available capacity, response times, and infrastructure costs.

Next

Anubis

SecurityInfrastructure

A web firewall that uses configurable request policies and browser challenges to reduce unwanted crawler traffic.

Saved github.comrepository

Colibri

Models & Inference

An inference project that streams mixture-of-experts model weights from storage to work within limited memory.

Saved github.comrepository