LLM Pipeline Analysis

Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.

bbuf Updated

File contents

bbuf/ai-infra-auto-driven-skills commit 2b5569e0f8

Frequently asked questions

npx get-skill add bbuf/llm-pipeline-analysis