⚡ Performance Engineering - buckman · Scour

From 800ms to ~25ms: harness-driven optimization of a CUDA matmul kernel 📊Performance Tools

github.com·3d·Hacker News

The Two Thread IDs of macOS: Measuring P/E Core Usage on Apple Silicon 🚀Performance

bazhenov.me·2d

Your AM5 board has a hidden BIOS setting for even better DDR5 performance, and no, it's not EXPO 🏷️Memory Tagging

xda-developers.com·5h

Java Performance Tuning and Event-Driven System Design for Scalable Systems ⚙️Systems Programming

·2d

GPU vs CPU Inference: 5 Scenarios, Real Costs & Latency 💰Compute Costs

tildalice.io·3d

Intel VP claims up to 30% of CPU performance is untapped by modern games — software optimization is critical to unlocking full potential of hybrid CPUs 🚀Performance

tomshardware.com

·1d

The great workload reshuffle: Choices for AI and analytics 📊Compute Markets

·3d

sdeonvacation/throttle: A sophisticated task execution framework in Java that automatically adapts to system resource availability. 🚀Performance

github.com·1d·DEV

The Hidden Bottlenecks in LLM Inference and How to Fix Them 🤖LLM Inference

digitalocean.com·4d

Masking Ordering Failures in BFT SMR via Proactive Pre-Commit Execution ⏱️Durable Execution

eprint.iacr.org·4d

Red Hat Performance and Scale Engineering 🔄AI Workflows

2026 State of Kubernetes Resource Optimization: CPU at 8%, Memory at 20%, and Getting Worse ☸️K8S

cast.ai·5d·Hacker News

SONIC: Concurrent Oblivious RAM & Data Structures for Low-Latency and High-Throughput 🏷️Memory Tagging

5.6x throughput on Kimi K2.6 by speculating less 📊Performance Tools

huggingface.co·5d·Hacker News

Exploring The Workloads Where The AMD Ryzen 9 9950X3D2 Makes A Lot Of Sense Review 🚀Performance

phoronix.com·3d

Luce-Org/lucebox-hub: Lucebox optimization hub: hand-tuned LLM inference, built for specific consumer hardware. 🟩Nvidia

github.com·6d·Hacker News

asyncio vs threading vs multiprocessing: Real Latency 🚀Performance

tildalice.io·6d

2026 State of Kubernetes Optimization Report ⚓Kubernetes

cast.ai·4d·Hacker News

The LLM Inference Trilemma: Throughput, Latency, Cost ⚡Inference

digitalocean.com·4d

The Hidden Cost of Cold Starts in Serverless AI Workloads 🏛Sovereign AI Infrastructure

digitalocean.com·6d

Log in to enable infinite scrolling