📊 Columnar Storage - mando · Scour

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving 🏗️System Design

Different Prompts, Different Ranks: Prompt-aware Dynamic Rank Selection for SVD-based LLM Compression 💬LLMs

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control 💬LLMs

Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction 🏗️System Design

arxiv.org·5d·Hacker News

Grid-Orch: An LLM-Powered Orchestrator for Distribution Grid Simulation and Analytics 💬LLMs

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction 💬LLMs

31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding 🏗Computer Architecture

High-arity Sample Compression 🔍Vector Search

Qwen-Image-VAE-2.0 Technical Report 📊Embeddings

Outstanding TC Enhancement in 5d-3d Y2NiIrO6 by Compression 🎮Game Development

MedCore: Boundary-Preserving Medical Core Pruning for MedSAM 💬LLMs

Cloud Storage Rapid: Turbocharged object storage for AI and analytics ☁️Cloud Computing

cloud.google.com·6d·Hacker News

Log in to enable infinite scrolling