Serverless LLM Serving for Everyone.
Privacy-first real-time face mask detection in the browser using YOLO-Fastest, NCNN, C++, and WebAssembly.
LLM Inference on AWS Lambda
Python SDK and CLI for modelz.ai, which is a developer-first platform for prototyping and deploying machine learning models.
A production-grade Android application demonstrating Serverless GPU Inference integration. Features a robust Retry Policy for cold starts, Foreground Services for long-running generation, and Clean Architecture with Jetpack Compose & Koin. Handles Text-to-Image (SDXL) and Image-to-Image pipelines via Hugging Face.
Queue-driven, scale-from-zero GPU inference for any Kubernetes — bursts to cross-region VMs when GPUs run dry
Deep learning pipeline for urban sound classification with a ResNet18 backbone, ONNX optimization, and a FastAPI deployment layer.
An enterprise-grade, serverless RAG pipeline transforming multi-page PDF documents into interactive, context-aware knowledge networks using modern LangChain (LCEL) architectures.
Autonomous DevSecOps & Data Agent with Blast Radius Zero Sandboxing on Vultr | Vultr: Agent Rush Hackathon Track 1
Page, ticket or ignore: 200 alerts, one written on-call policy, eight models on DigitalOcean Serverless Inference. Measures missed pages, cost and latency, and what the model routers pick.
Can a vision model read your Grafana panel? 100 Grafana-style panels with known answers, vision models on DigitalOcean Serverless Inference, and an on-call bot that checks the model's read against the alert.
AI-assisted patient intake with a doctor in the loop — Vultr Agent Rush Hackathon, Challenge 2.
Recover a forgotten crypto wallet password from what you half remember, inside a sealed Vultr box that cannot leak it. Vultr Agent Rush, Blast Radius Zero.
To associate your repository with the serverless-inference topic, visit your repo's landing page and select "manage topics."