Software-Delivered AI Inference

Neural Magic helps developers in accelerating deep learning performance using automated model sparsification technologies and inference engines. Download our sparsity-aware inference engines and open source tools for fast model inference.

• nm-vllm: A high-throughput and memory-efficient inference engine for LLMs, incorporating the latest LLM optimizations like quantization and sparsity
• DeepSparse: Inference runtime offering GPU-class performance on CPUs and APIs to integrate ML into your application
• SparseML: Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
• SparseZoo: Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes