44 projects with the selected classifier
TensorFlow is an open source machine learning framework for everyone.
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference.
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
NVIDIA cuQuantum Python
A machine learning package
NVIDIA cuTENSOR
The Holoscan SDK: building high-performance AI streaming applications
OpenLLM Core: Core components for OpenLLM.
OpenLLM: Operating LLMs in production
Supported by
