NVIDIA Model Optimizer: A Unified Toolkit for Quantization, Pruning, and Distillation
NVIDIA Model Optimizer (ModelOpt) unifies NVFP4/FP8 quantization, structured pruning, and distillation to accelerate inference across TensorRT-LLM, vLLM, and SG
#TensorRT-LLM
TAU-HOME.COM stories tagged TensorRT-LLM.
The Infrastructure Behind the AI Boom: 10 Essential Open-Source Repositories
A guide to 10 open-source repositories driving the AI boom, covering high-throughput serving, local execution, unified gateways, vector search, and distributed