Dissecting Batching Effects in GPT Inference
le.qun.ch·22h·
Discuss: Hacker News
🏗️Hardware Architecture
STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
arxiv.org·17h
⚙️Query Compilers
Tuning guide for AMD Amazon EC2 instances
aws.amazon.com·2h
📈Performance Profiling
AlloyDB on Axion-powered C4A instances is generally available
cloud.google.com·4h
📊Column Stores
Creating a market-viable app in less than Week
dev.to·22h·
Discuss: DEV
🏗data engineering
Automate advanced agentic RAG pipeline with Amazon SageMaker AI
aws.amazon.com·3h
📊Data Lineage
Speculative cascades — A hybrid approach for smarter, faster LLM inference
research.google·23h·
Discuss: Hacker News
⚙️Query Compilers
Choosing Rust for LLM-generated code
runmat.org·3h·
Discuss: Hacker News
🦀Rust Scientific
Analog Plus 3D Optics to Accelerate AI inference and Combinatorial Optimization (Microsoft, Cambridge)
semiengineering.com·4h
💡Optical Computing
How do AI models generate videos?
technologyreview.com·11h
🤖AI
The best Make alternatives in 2025
zapier.com·17h
🏗data engineering
Your APIs Are Costing More Than You Think
thenewstack.io·4h
👁️Observability
Docling: The Document Alchemist
towardsdatascience.com·4h
📓Jupyter
Flexynesis: A deep learning toolkit for bulk multi-omics data integration for precision oncology and beyond
nature.com·11h
🧬Bioinformatics
LLM-Generated Rules Engines for LLM Explainability
brain.co·9h·
Discuss: Hacker News
🔄Feed Aggregation
Test-Time Compute: The Hidden Revolution Powering Next-Generation AI Reasoning
dev.to·6h·
Discuss: DEV
🎮Reinforcement Learning
K2-Think: A Parameter-Efficient Reasoning System
arxiviq.substack.com·5h·
Discuss: Substack
⚙️Query Compilers
An introduction to program synthesis
mchav.github.io·21h·
⚙️Query Compilers
Optimizing 100B ClickHouse Events
replo.computer·16h·
Discuss: Hacker News
ClickHouse
Decompiling the GPL violated Linux kernel using Evolutionary Algorithms
far.chickenkiller.com·12h·
Discuss: Hacker News
⚙️Query Compilers