GitHub

FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

This project has no flash-attn dependency, no custom triton kernel. Everything is implemented with FlexAttention. The code is commented, the structure is flat. Read the accompanying write-up: vLLM ...
IEEE

Membership Inference Attacks and Differential Privacy: A Study Within the Context of Generative Models

Abstract: Membership attacks pose a major issue in terms of secure machine learning, especially in cases in which real data are sensitive. Models tend to be overconfident in predicting labels from the ...
GitHub

inference-gateway/browser-agent

A enterprise-ready Agent-to-Agent (A2A) server that provides AI-powered capabilities through a standardized protocol.
IEEE

Hybrid Sentiment Analysis for Azerbaijani: Lexicon-Driven Fuzzy Inference vs. Machine Learning Approaches

Abstract: This work focuses on researching methods for Sentiment Detection of text using Fuzzy Control Systems (FCS). The main goal of this system is to implement membership rules through statistical ...
SciELO

Comparison of the effect of a lower versus a higher PEEP strategy on clinically relevant outcomes in invasively ventilated patients without acute respiratory distress syndrome ...

Background: The effect of different levels of positive end-expiratory pressure in invasively ventilated critically ill patients remains a matter of debate. The REstricted versus Liberal Positive ...
SiliconANGLE

AI inference startup Runware raises $50M to make AI run faster

Artificial intelligence startup Runware Ltd. wants to make high-performance inference accessible to every company and application developer after raising $50 million in an early-stage funding round.