📊 Columnar Storage - mando · Scour

HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts 📊Embeddings

Agentic AI token compression using Haskell λFunctional Programming

blog.dan-gilmour.com·5d·Hacker News

AI + BI Convergence: Engineering the 10M-Row AI BI Agent 🤖AI

dattasable.com·4d·DEV

AMD's DGF SuperCompression Shrinks Geometry File Size by 22% 💻Terminal Emulators

techpowerup.com·6d

Compute Optimal Tokenization (2 minute read) 💬LLMs

arxiviq.substack.com

SAP: Latest news and insights ⚙️Data Engineering

Complete End-To-End Closed-Loop Product Yield Ramp And Learning 🏗Computer Architecture

semiengineering.com·5d

Securing client confidentiality at scale: Automated data discovery and governed analytics for legal workloads ⚙️Data Engineering

aws.amazon.com·4d

Netflix Serves 84% of Query Results from Cache with Interval-Aware Caching in Apache Druid 🦆DuckDB

Bridging the (Analytics) Culinary Gap ⚙️Data Engineering

mlops.community·4d

sqliteai/sqlite-columnar: Column-oriented analytics for SQLite, designed for fast local analytical queries with benchmarked speedups of up to 130,000x over standard SQLite scans on selected workloads. 🗃️SQLite

github.com·6d·Hacker News, Hacker News, Hacker News

Grafana's Pyroscope 2.0 Makes Continuous Profiling Practical at Scale 📉Grafana

duckdb/pg_duckdb: DuckDB-powered Postgres for high performance apps & analytics. 🦆DuckDB

github.com·4d·Hacker News

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression 🏗Computer Architecture

MERBIT: A GPU-Based SpMV Method for Iterative Workloads 🏗Computer Architecture

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression 🏗Computer Architecture

GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression 🤖LLM

OpenZL: Using Graphs to Compress Smaller and Faster 🏗Computer Architecture

From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation 🔍Vector Databases

NCCLZ: Compression-Enabled GPU Collectives with Decoupled Quantization and Entropy Coding 🏗️System Design

Log in to enable infinite scrolling