Skip to content

MarkTechPost - 2026-05-25

2 items collected.


1. Together AI Open-Sources OSCAR: An Attention-Aware 2-Bit KV Cache Quantization System for Long-Context LLM Serving

Author: Asif Razzaq
Published: 5/25/2026, 9:24:31 PM
Categories: AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, Machine Learning, New Releases, Open Source, Software Engineering, Staff, Tech News, Technology, Uncategorized

Together AI has released OSCAR (Offline Spectral Covariance-Aware Rotation), an INT2 KV cache quantization method for long-context LLM serving. Unlike prior rotation-based approaches that apply data-oblivious Hadamard transforms, OSCAR derives separate rotations for keys and values from attention-aw...

📖 Read original article


2. Step by Step Guide to Build and Compare FedAvg and FedProx Federated Learning on Non-IID CIFAR-10 with NVIDIA FLARE

Author: Sana Hassan
Published: 5/25/2026, 8:26:40 PM
Categories: Artificial Intelligence, Editors Pick, Federated Learning, Software Engineering, Staff, Technology, Tutorials

In this tutorial, we build an advanced federated learning experiment with NVIDIA FLARE. We compare FedAvg and FedProx on a non-IID CIFAR-10 setup, where client data is split using a Dirichlet distribution to simulate realistic label imbalance across federated sites. We use the NVFlare Job API to def...

📖 Read original article