Trying Out C++26 Executors
🌊Glommio
Flag this post
Strix Halo, Debian 13@6.16.12&6.17.8, Qwen3Coder-Q8 CTX<=131k, llama.cpp@Vulkan&ROCm, Power & Efficiency
🔄Glommio vs Tokio
Flag this post
Built an "Operating System" for AI agents that actually survives when shit breaks (offline-first, self-healing)
☁️Cloudflare Workers
Flag this post
The Engineering Guide to Efficient LLM Inference: Metrics, Memory, and Mathematics
pub.towardsai.net·2d
📊Profile-Guided Optimization
Flag this post
Pollianna
🔭OpenTelemetry
Flag this post
OSS Friday Update
🌊Glommio
Flag this post
clock_settime() latency surprisingly doubling from CLOCK_REALTIME to CLOCK_MONOTONIC!
🕐Vector Clocks
Flag this post
How Google Does It: Building the largest known Kubernetes cluster, with 130,000 nodes
☸️Kubernetes
Flag this post
Learning AI From Scratch: Streaming Output, the Secret Sauce Behind Real-Time LLMs
⏰Timely Dataflow
Flag this post
EP190: Cloudflare vs. AWS vs. Azure
blog.bytebytego.com·14h
🔭Tracing
Flag this post
October 2024 Progress in Guaranteed Safe AI
lesswrong.com·2d
🧮SMT Solvers
Flag this post
Loading...Loading more...