TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Updated 2026-01-13 13:20:15 +08:00
A modular graph-based Retrieval-Augmented Generation (RAG) system
Updated 2026-01-13 10:00:21 +08:00
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
Updated 2025-04-22 21:49:27 +08:00