Skip to content
    Ready to clone

    Blueprints that turn weeks into minutes

    Ready-to-run templates for inference, fine-tuning, and batch jobs: fast starts for builders who still want control.

    Customer Favorites

    Fine-tuning

    Reinforcement Learning Fine-tuning with EasyR1

    Use reinforcement learning to train models that reason step by step. Walks through GRPO training on FlexAI using EasyR1, with a before/after comparison of output quality.

    Training

    GRPO Training on Vision-Language Models

    Fine-tune vision-language models to reason over images using reinforcement learning. Runs a full TRL, LoRA, vLLM, and DeepSpeed ZeRO-3 stack on FlexAI.

    Inference

    Multi-Agent Orchestration with LangGraph

    Deploy a multi-agent system where specialised AI agents collaborate under a central supervisor. Built with LangGraph and powered by FlexAI inference endpoints.

    Fine-tuning

    Train and Serve a French LLM with LlamaFactory

    Fine-tune an LLM on your own data and serve it as a live API endpoint. Takes Qwen2.5-7B from training to production inference on FlexAI.

    Inference

    Text-to-Video Inference

    Serve Wan2.2-T2V-A14B as a scalable API endpoint on FlexAI in minutes. No GPU management required.

    Inference

    RAG Application with LangChain

    Answer questions over your own documents using a LangChain RAG pipeline backed by a FlexAI inference endpoint.

    Need a custom blueprint?

    Our team can help you design infrastructure patterns tailored to your specific workload requirements.

    Talk to us