FriendliAI

Fastino Labs is an AI company that builds open-weight language models for agentic AI. Its models are intended for fast type decisions such as intent routing, fact-checking, hallucination checks, and browser-agent tasks, and the video describes them as available for local use and through an inference API. The company’s site identifies GLiNER, GLiGuard, and the Fastino fine-tuning agent among its research and models.

Together AI (branded Together) operates an "AI native cloud": a platform for deploying, running, and scaling AI models and applications. The service provides infrastructure and tooling for developing and serving machine learning and large language models.

Fireworks AI is a training and inference platform for transforming open models into specialized, deployable AI systems. Its training offerings range from guided runs, where the platform helps define the task and plan, through configuration-led managed training, to user-written training logic with custom losses, trainers, and reinforcement-learning loops; trained checkpoints can be deployed to production. Its inference service supports open models and customer-trained versions through serverless, dedicated on-demand, and reserved deployments, with an optimized inference engine and OpenAI- and Anthropic-compatible interfaces. Fireworks also provides a model library for running open-source models and supports the continuous train-and-serve workflow described by the videos, including monitoring, hot-loading new weights without downtime, and matching training and serving numerics.

Agents That Own Their Inference is a workshop resource for building and operating production AI agents on dedicated GPUs. Its Jupyter notebooks, Kubernetes manifests, load-testing utilities, evaluation code, and Terraform setup guide participants through running a vLLM OpenAI-compatible endpoint and measuring inference behavior, including prefill and decode, time to first token, token generation time, KV-cache capacity, batching, queueing, and saturation. The workshop establishes a baseline, changes serving configurations, reruns realistic load tests, and evaluates output quality alongside throughput and latency. Exercises cover BF16-to-FP8 quantization, speculative decoding with a draft model, vLLM serving-policy changes, dense versus mixture-of-experts behavior, and deploying an agent on the measured inference endpoint. It can use an Akamai-hosted workshop namespace or a participant's Kubernetes cluster with an NVIDIA GPU; the repository is licensed under Apache-2.0.