A collection of recipes/notebooks showcasing use-cases of open-source models with Qubrid AI.

Testing Function Calling while running llama3.1 locally using ollama

Fuzzy Logic Toolbox with GUI and Files Analysis.

A high-performance request router for vLLM — smart load balancing, response caching, prefill/decode disaggregation, semantic routing, Anthropic/OpenAI API translation, and operational tooling out of the box.

Simple framework for LLM inferencing

Python codes generation from latex expressions. Using synthetic dataset and CodeT5-base model.

🦀 A barebones inferencing server in Rust, using Hyper for HTTP logic and ORT for inferencing models. Containerized and easily hostable. Complete control over type of model and inferencing behavior!

Classification of sperm heads based on its morphological quality via Mask-RCNN

An LLM inferencing benchmark tool focusing on device-specific latency and memory usage