Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs. Enterprise-grade LLMOps.
@invergent-ai/surogate
Implement a new model architecture using the Surogate Python DSL. Use when the user wants to add support for a new HuggingFace model (e.g., "add Gemma2 support", "implement DeepSeek model", "add new architecture"). Guides through creating block, model, and HF mapping definitions.
