A high-throughput and memory-efficient inference and serving engine for LLMs
-
Updated
Jun 2, 2024 - Python
PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook's AI Research lab.
A high-throughput and memory-efficient inference and serving engine for LLMs
FlashInfer: Kernel Library for LLM Serving
A guidebook to explore Neural Networks.
Data mining, machine learning, and deep learning sample code
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
Tools for understanding how transformer predictions are built layer-by-layer
Kotlin Multiplatform sample application.
NCF Paper Implementation (Pytorch)
Online Handwritten Text Recognition (HTR) system implemented with PyTorch. Based on https://doi.org/10.1007/s10032-020-00350-4.
Cerebral Tumor Analysis and Segmentation Web Application
scalable molecular simulation
Convolutional Neural Network inference library running on CUDA
Accelerate your training with this open-source library. Optimize performance with streamlined training and serving options with JAX. 🚀
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Serve, optimize and scale PyTorch models in production
Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
AI Models for Playing Super Mario Bros
Created by Facebook's AI Research lab (FAIR)
Released September 2016
Latest release about 2 months ago