Fireworks Training Agent

A managed fine-tuning service from Fireworks AI that lets users select a supported base model, provide training data and configuration, and launch jobs through the Fireworks UI, CLI, or API without writing custom training infrastructure. Fireworks-managed infrastructure handles scheduling, training, checkpointing, and model output; the same jobs can also be configured with an agent. Training data uses the OpenAI-compatible chat-completion format, and the UI provides visual monitoring of training metrics. Managed training supports supervised fine-tuning for text and vision models, preference optimization with DPO or ORPO, and LoRA adapter training. Supported model families include DeepSeek, Qwen, Kimi, Gemma, GLM, and Llama, with eligibility and context limits determined per model and method. Per-step loss and learning-rate artifacts are retained for seven days unless longer-term history is configured through Weights & Biases. Full-parameter tuning is available through Fireworks' separate Training API; managed reinforcement fine-tuning is deprecated.

Fireworks AI's training API is a programmatic model-training offering for ML engineers who need to define custom training loops and loss functions beyond managed training. The video describes support for supervised fine-tuning, reinforcement fine-tuning, and direct preference optimization (DPO), as part of Fireworks AI's train-and-serve workflow for open 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.

Fireworks is an AI platform that provides training and inference tools to transform open models into domain-specific or specialized intelligence. The service offers capabilities for model training, fine-tuning and serving to support customized AI deployments.

Fireworks AI's inference engine for serving AI models. It uses custom-built CUDA kernels that can be optimized for a customer's workload to target latency and performance requirements. The video credits FireAttention and related Fireworks serving work with enabling 13× faster inference for Cursor's Composer 2.