A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Instructions file CodexOpenCode
Instructions for NVIDIA/Model-Optimizer, covering agent instructions for modelopt, repository orientation, coding guidelines, iterative development and contributing and pr readiness.
Instructions file
Instructions for NVIDIA/Model-Optimizer, a project described as: A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT…