A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

General Information, model certifications, and benchmarks for nm-vllm enterprise distributions

Neural network model repository for highly sparse and sparse-quantized models with matching sparsification recipes

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Sparsity-aware deep learning inference runtime for CPUs

ML model optimization product to accelerate inference.