A high-throughput and memory-efficient inference and serving engine for LLMs

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

🤗 Optimum Intel: Accelerate inference with Intel optimization tools

Examples for using ONNX Runtime for machine learning inferencing.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A collection of pre-trained, state-of-the-art models in the ONNX format