Popular repositories Loading

1. AITemplate AITemplate Public

   Forked from facebookincubator/AITemplate

   AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

   Python

2. XNNPACK XNNPACK Public

   Forked from google/XNNPACK

   High-efficiency floating-point neural network inference operators for mobile, server, and Web

   C

3. distributed-llama distributed-llama Public

   Forked from b4rtaz/distributed-llama

   Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.

   C++