Features
100% MySQL compatible – no code changes needed
HTAP (transactional + analytical processing)
Cost-based and ML-based optimizer
In-memory columnar analytical engine
Real-time TP-to-AP propagation
Native machine learning via LightGBM
On-database LLM inference via ONNXRuntime
Vector processing support
Multi-model support (relational, document, etc.)
Multi-language support (SQL, etc.)
Intelligent workload offloading
Freemium pricing with free tier
Automated neural architecture search (NAS)
INT8 and FP16 quantization
Hardware-aware optimization for NVIDIA GPUs
Model compression and pruning
NVIDIA TensorRT integration
Benchmarking and performance profiling
Deployment to cloud, edge, and mobile
Custom training with NAS-driven architectures
Computer vision model optimization
Deci AI Studio for model development
Automatic compilation pipeline for target hardware
