GitHub

A storage solution for PyTorch tensors with distributed tensor support.

TorchStore provides a distributed, asynchronous tensor storage system built on top of Monarch actors. It enables efficient storage and retrieval of PyTorch tensors across multiple processes and nodes ...
GitHub

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

09/04/2025 4.1.0: Meituan LongCat Flash Chat, Llama 4, GPT-OSS (BF16), and GLM-4.5-Air support. New experimental mock_quantization config to skip complex computational code paths during quantization ...
IEEE

Multi Fruit Classification and Grading Using Transfer Learning

Abstract: A unified AI-based approach in classification and grading for multiple fruits could effectively result in getting the quality of apples, bananas, and oranges, with a classification accuracy ...
Geeky Gadgets

NVIDIA Buys Groq for $20B : Licensing Pact, Faster Inference Chips & CUDA Support Ahead

What does a $20 billion acquisition mean for the future of AI hardware? That’s the question on everyone’s mind as NVIDIA, a titan in the tech world, officially acquires Groq, a rising star in AI ...