Python AxmlParser

Fast CUDA Kernels for ResNet Inference. Using Winograd algorithm to optimize the efficiency of co...

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, ...

SGLang is a fast serving framework for large language models and vision language models.

tabnotes

Benchmarking code for running quantized kernels from vLLM and other libraries

IQ of AI

ModelScope: bring the notion of Model-as-a-Service to life.