skills.rest
zystem-io
zystem-ioOFFICIAL
Explore all skills by this author →
WebsiteGitHub

install-zymtrace-profiler

Deploy the zymtrace profiler agent to Kubernetes, Docker, or bare-metal and connect it to a backend gateway.

5|1|Updated May 17, 2026
Search Tags:#kubernetes#helm#cuda#profiler#zymtrace#daemonset#gpu-metrics
One-click install
npx skills add https://github.com/zystem-io/zymtrace-skills --skill install-zymtrace-profiler
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: install-zymtrace-profiler
Source: https://github.com/zystem-io/zymtrace-skills/tree/main/zymtrace/skills/install-zymtrace-profiler
Command: npx skills add https://github.com/zystem-io/zymtrace-skills --skill install-zymtrace-profiler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill installs the zymtrace profiler agent so your cluster can collect continuous CPU and (optionally) CUDA GPU profiling data and forward it to the existing zymtrace backend gateway.

Core Features & Use Cases

  • Helm DaemonSet / Kubernetes deployment: Installs the profiler across all nodes (GPU-capable scheduling optional) and connects it to your backend gateway endpoint.
  • Multi-platform install options: Supports Kubernetes without Helm (manifest), Docker single-host, and bare-metal binary installs with systemd.
  • CPU-only vs CUDA GPU profiling: Enforces the CUDA 12.x+ requirement for GPU profiling and configures GPU metrics and framework metrics for vLLM, SGLang, and Dynamo-Triton where available.
  • Air-gapped / private registry support: Mirrors and configures the profiler image for restricted environments.
  • Verification and guardrails: Runs a post-install verification workflow to confirm license validity and backend connectivity, and routes GPU/workload setup needs clearly.

Quick Start

Tell the AI to install the profiler with GPU support on your EKS cluster and connect it to your backend gateway, then follow the verification prompts until the agent confirms backend streaming.

Frequently Asked Questions about install-zymtrace-profiler

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy a CPU profiler as a Kubernetes DaemonSet using Helm?▼

To deploy a Kubernetes CPU profiler as a Helm DaemonSet, install the zymtrace profiler agent across all cluster nodes and wire it to your backend gateway endpoint to start collecting continuous profiling data.

Can I collect CUDA GPU profiling metrics in Kubernetes?▼

Yes, you can collect CUDA GPU profiling metrics in Kubernetes by configuring the profiler agent with GPU-capable scheduling. You must enforce CUDA 12.x or higher to enable GPU metrics and framework metrics for vLLM, SGLang, and Dynamo-Triton.

Does the zymtrace profiler work in air-gapped environments with private registries?▼

Yes, the zymtrace profiler works in air-gapped environments by mirroring the profiler image to a private registry. It configures the agent for restricted environments to ensure continuous CPU and GPU profiling data collection.

What is the correct format for the backend gateway endpoint when installing the profiler?▼

The correct format for the backend gateway endpoint is strictly host:port. You must never use a URL with https:// when resolving the backend gateway, ensuring the profiler agent can successfully stream profiling data to the UI.

Can I run continuous profiling on bare-metal servers without Docker?▼

Yes, you can run continuous profiling on bare-metal servers without Docker by installing the profiler agent as a binary with systemd. This setup supports both CPU-only and optional CUDA GPU profiling metrics depending on your hardware.

How do I verify license validity and backend connectivity after installing the profiler?▼

To verify license validity and backend connectivity after installing the profiler, run the built-in post-install verification workflow. This confirms your license is valid and checks that the agent is actively streaming data to the backend gateway.

Related Skills

Explore More Software Engineering Skills→
0xb11a0xb11a

openclaw-setup

Provision and deploy OpenClaw agents across Docker or Bare-Metal paths.

Official
Advanced
flashinfer-aiflashinfer-ai
264

extract-kernel-definitions

Extract GPU kernel schemas from SGLang models into deduplicated Definition JSON files.

Official
Advanced
zystem-iozystem-io
5

troubleshoot-zymtrace-profiler

Diagnoses zymtrace profiler agent failures in Kubernetes using kubectl and helm workflows.

Official
Intermediate
MisLinkMisLink

beyla

Deploy eBPF probes to capture HTTP/gRPC traffic and emit traces and metrics.

Community
Advanced