vLLM Performance Tuning: The Ultimate Guide to xPU Inference Configuration
cloud.google.com·12h
🏗️AI Infrastructure
google/highway
github.com·2d
🔌Embedded Rust
Whatever Happened To … Webrings (2012)
insufficientscotty.com·19h·
Discuss: Hacker News
📝CMS
How Should a CMS Repository Understand the Content Within It?
deanebarker.net·2d·
Discuss: Hacker News
🗃️database engineering
NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit
developer.nvidia.com·1d·
Discuss: Hacker News
⚡Hardware Acceleration
MSNav: Zero-Shot Vision-and-Language Navigation with Dynamic Memory and LLM Spatial Reasoning
arxiv.org·43m
🏗️AI Infrastructure
The Impact of Artificial Intelligence on Human Thought
arxiv.org·43m
🏠Self-hosted AI
ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion
arxiv.org·43m
🎙️Whisper
Measuring Large Language Models Dependency: Validating the Arabic Version of the LLM-D12 Scale
arxiv.org·43m
🎙️Whisper
SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation
arxiv.org·43m
🧮Algorithmic Cooking
Try My ~3.5 Million Parameters Model Instead for ✨😉
dev.to·21h·
Discuss: DEV
🎙️Whisper
PediatricsMQA: a Multi-modal Pediatrics Question Answering Benchmark
arxiv.org·1d
🏗️AI Infrastructure
Meta-R1: Empowering Large Reasoning Models with Metacognition
arxiv.org·43m
🏗️AI Infrastructure
Demographic Biases and Gaps in the Perception of Sexism in Large Language Models
arxiv.org·43m
💻Local LLMs
Effect of Performance Feedback Timing on Motor Learning for a Surgical Training Task
arxiv.org·43m
🧠Neuromorphic Hardware
Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
arxiv.org·43m
💻Local LLMs
Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs
arxiv.org·1d
🎙️Whisper
On Zero-Shot Reinforcement Learning
arxiv.org·1d
🏗️AI Infrastructure
Being Kind Isn't Always Being Safe: Diagnosing Affective Hallucination in LLMs
arxiv.org·43m
🏠Self-hosted AI
GeoMAE: Masking Representation Learning for Spatio-Temporal Graph Forecasting with Missing Values
arxiv.org·5d
🤝Federated Learning