📦 Parquet - buckman · Scour

🛠️ Crompressor: Reality Compilation - Teaching Data Centers to Recognize Their Own Data - 🔒 -P2P FUSE file system reducing data payload to 20% ⚡gRPC

dev.to·6d·DEV·

TFMV/porter: Arrow Flight SQL Server for DuckDB 🦆DuckDB

github.com·1d·

Structural modifications in strain-engineered bilayer nickelate thin films 🔐Post-Quantum Cryptography

nature.com

·18h·

Google's TurboQuant saves memory, but won't save us from DRAM-pricing hell 📊Compute Markets

theregister.com·12h·

PrismML, which says its 1-bit LLM achieves radical compression without sacrificing performance, comes out of stealth with $16.25M in SAFE and seed funding (Stev... 💻Tech News

techmeme.com·1d·

From Stream to Strategy: How TOON Enhances Real-Time Kafka Processing for AI 🏛Sovereign AI Infrastructure

dzone.com·5d·

Agentic Architectures — Article 4: Agentic Protocols (MCP and A2A) 🎼Agent Orchestration

medium.com

·1d·DEV·

Google’s TurboQuant Compression Could Increase Demand For AI Memory ⚡Quantization

oodaloop.com

·6d·

Deep Learning Weekly: Issue 448 📱Edge AI

deeplearningweekly.com·6d·

pg-warehouse - A local-first data warehouse at scale without over Engineering that mirrors PostgreSQL data 🦆DuckDB

dev.to·2d·DEV·

SharpAI/SwiftLM: ⚡ Native Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, + iOS iPhone app. 🤖LLM Inference

github.com·1d·Hacker News, Hacker News·

HDF5 vs. TsFile: Efficient Time-Series Data Storage 📊Data Science

dev.to·1d·DEV·

russellromney/turbolite: SQLite VFS with sub-50ms cold queries from S3 + page-level compression and encryption 🚀Performance

github.com·6d·Hacker News·

Why Inference Compression Compounds for Modular Agents 🤖LLM Inference

dev.to·2d·DEV·

I Tested TurboQuant KV Cache Compression on Consumer GPUs. Here's What Actually Happened. 📊Benchmarking

dev.to·2d·DEV·

ClickHouse Has a Free Column-Oriented Database — Query Billions of Rows in Milliseconds 🦆DuckDB

dev.to·5d·DEV·

Design-to-Code Compression: How AI Closes the Figma Gap ✍️Prompt Engineering

dev.to·1d·DEV·

Google's Cache Compression, Siri's Open Door, and the CFO Agent Test 🤖LLM Inference

dev.to·6d·DEV·

I shipped Google's TurboQuant as a vLLM plugin 72 hours after the paper — here's what nobody else tested 🤖LLM Inference

dev.to·5d·DEV·

Hi I'm Ruddy 🗒️Obsidian

dev.to·4d·DEV·

Loading more...