Grok open release

Official inference framework for 1-bit LLMs

Official inference library for Mistral models

A Datacenter Scale Distributed Inference Serving Framework

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Intel XeSS SDK

NVIDIA Inference Xfer Library (NIXL)

An Open Framework for Federated Learning.

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmer…

An innovative library for efficient LLM inference via low-bit quantization

Intel® Extension for TensorFlow*

SPEAR: A Simulator for Photorealistic Embodied AI Research

SYCL implementation of Fused MLPs for Intel GPUs

Real-time human detection and tracking camera using YOLOV5 and Arduino