An MLOps workflow for training, inference, experiment tracking, model registry, and deployment.

Computes CT contrast phase and GI tract contrast using TotalSegmentator and ML

A comprehensive .NET MAUI plugin for ML inference with ONNX Runtime, CoreML, and platform-native acceleration support

gRPC server for Machine Learning (ML) Model Inference in Rust.

EcoChain-ML is a hybrid energy-aware ML framework integrating a lightweight PoS blockchain layer and renewable-aware scheduling. Built to simulate green computing strategies on a single PC, it evaluates energy, latency, and sustainability trade-offs.

[TPDS 2025] EdgeAIBus: AI-driven Joint Container Management and Model Selection Framework for Heterogeneous Edge Computing

ML service for cats that actually learn stuff. PPO brains, personality drift, mood system.

Fast GPU-accelerated speech-to-text in Rust. INT8 quantization, streaming, speaker diarization

🐱 Create a living cat AI that exhibits emotions, reactions, and realistic behavior for an engaging and interactive experience.

hardware-aware ml deployment optimization and recommendation framework

ML inference platform: upload dataset → LoRA fine-tune (HuggingFace + PEFT) → ONNX Runtime inference, async training via Celery, model registry in MinIO, Prometheus/Grafana.

Machine learning system for on-device inference that analyzes patrol notes and predicts violation type and severity using NLP embeddings and trained classification models.

Unified memory ML inference engine for AMD APU (RDNA 3.5 / gfx1150) — Custom HIP kernels with 2.2x speedup over standard allocation

Production-style real-time ML feature store with low-latency inference

Image-based game controller classifier UI. Upload photos to identify PS, Xbox, Nintendo, and Gamecube controllers using a trained ML model.

Runtime-agnostic TypeScript API framework — the same App runs unmodified on Node, AWS Lambda, Cloudflare Workers, Bun, and Deno, with built-in security middleware, independent background threads for bots/pollers, and serverless-aware ML inference.

Dockerized Django application for handwritten math expression recognition using a CNN model, with end-to-end ML pipeline and cloud-ready deployment.

🚀 Event-driven ML inference pipeline using AWS Step Functions and Lambda. Orchestrates a SageMaker image classification workflow with automated confidence-threshold filtering and state machine error handling.

Optimized GPU/CPU speech-to-text service using faster-whisper for low-latency transcription pipelines.