🤖 AI - surajkadapa · Scour

Exploring the Efficiency of 3D-Stacked AI Chip Architecture for LLM Inference with Voxel ⚡Hardware Acceleration

Automated deep learning by recurrent hyperparameter optimization 📐Vector Search

AI academic search needs better frameworks for understanding and evaluation. These three librarian projects are a start 🎯BM25

aarontay.substack.com·1d·Substack

My New Ebook (Free Download): Quantization for Modern AI Systems 📉Embeddings Optimization

pawankjha.substack.com·3d·Substack

Category Theory for Tiny ML in Rust 📐Algorithms

hghalebi.github.io·1d·Hacker News

AI 101: What’s So Magical About Embeddings? 🔢Vector Databases

turingpost.com·6d

A decoder-only foundation model for time-series forecasting 📉Embeddings Optimization

research.google·6d

How AI can streamline your security testing 🎯Speculative Execution

redcanary.com·6d

Token Arena: A Continuous Benchmark Unifying Energy and Cognition in AI Inference ♟️Chess Engines

AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs 📉Embeddings Optimization

Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference ⚡Low-Latency Systems

LLM-Emu: Native Runtime Emulation of LLM Inference via Profile-Driven Sampling ⚡Vectorized Execution

AAFLOW: Scalable Patterns for Agentic AI Workflows 🌐Distributed Systems

Focus Session: Autonomous Systems Dependability in the era of AI: Design Challenges in Safety, Security, Reliability and Certification 🌐Distributed Systems

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters 🖥️GPU Computing

Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation 📉Embeddings Optimization

AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism 🔧Compilers

arxiv.org·5d·Hacker News

Stochastic Sparse Attention for Memory-Bound Inference ⚡Vectorized Execution

SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving ⚡Low-Latency Systems

AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework ♟️Chess Engines

Log in to enable infinite scrolling