note

RTX Inference Optimization for GoogleGemma 4 31B, 784x Scrapling Scraping Speedup, and Discussion on Fujitsu's 1-bit Quantization Technology

Three AI technology topics are gaining attention on X (Twitter). One is the RTX inference optimization for GoogleGemma 4 31B (up to 2.7x speedup) through a collaboration between NVIDIA and ggerganov.
GitHub

Python implementation of the TurboQuant and QJL vector quantization algorithms.

turboquant-py implements the TurboQuant and QJL vector quantization algorithms from Google Research (ICLR 2026 / AISTATS 2026). It compresses high-dimensional floating-point vectors to 1-4 bits per ...
InfoWorld

I ran Qwen3.5 locally instead of Claude Code. Here’s what happened.

You can now run LLMs for software development on consumer-grade PCs. But we’re still a ways off from having Claude at home. If you’ve been curious about working with services like Claude Code, but ...
IEEE

SQUAT: Stateful Quantization-Aware Training in Recurrent Spiking Neural Networks

Abstract: Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking ...
IEEE

End-to-End Workflow for Machine Learning-Based Qubit Readout With QICK and hls4ml

Abstract: We present an end-to-end workflow for superconducting qubit readout that embeds co-designed Neural Networks (NNs) into the Quantum Instrumentation Control Kit (QICK). Capitalizing on the ...
GitHub

Locally Optimized Product Quantization

This is Python training and testing code for Locally Optimized Product Quantization (LOPQ) models, as well as Spark scripts to scale training to hundreds of millions of vectors. The resulting model ...
Hosted on MSN

MI Physics Lecture Chapter 8; Energy Quantization

Physics and Python stuff. Most of the videos here are either adapted from class lectures or solving physics problems. I really like to use numerical calculations without all the fancy programming ...