From AI Flame Graph Analysis to Verified Fixes: A Coding-Agent Optimization Loop with OpenResty XRay

  • Prerequisite: OpenResty XRay must already be installed on the target machine
  • Your coding agent isn’t short on intelligence—it’s short on runtime visibility
  • Three optimization rounds: 336 → 4,457 → 26,028 → 29,968 RPS
  • Lua + C, two perspectives: why you shouldn’t try to optimize writev
  • FAQ
  • Prerequisite: OpenResty XRay must already be installed on the target machine
  • Your coding agent isn’t short on intelligence—it’s short on runtime visibility
  • Three optimization rounds: 336 → 4,457 → 26,028 → 29,968 RPS
  • Lua + C, two perspectives: why you shouldn’t try to optimize writev
  • FAQ

llama.cpp CPU Usage: 400% CPU Traced to ggml Hot Functions

  • Running llama.cpp and Observing 400% CPU Usage
  • Profiling llama.cpp CPU Usage with OpenResty XRay
  • Findings: The Hottest C++ Code Paths
  • What is OpenResty XRay
  • Running llama.cpp and Observing 400% CPU Usage
  • Profiling llama.cpp CPU Usage with OpenResty XRay
  • Findings: The Hottest C++ Code Paths
  • What is OpenResty XRay
Contact us

Love to hear from you, Get in touch 👋

Message was sent successfully!

Our Team will get back to you within 24 hours.
x