tpu-management: a Claude Code skill for running Gemma 4 on Cloud TPUs
7.8 relevance
Score Breakdown
technical depth 8
novelty 8
actionability 9
community 5
strategic 6
personal 9
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Directly relevant to AI agent orchestration and cloud infrastructure with a practical, installable tool for running LLMs on TPUs.
Summary
tpu-management is a Claude Code skill and MCP server that automates the full lifecycle of serving Gemma 4 on Cloud TPUs — from zone capacity sweeping and flex-start VM provisioning with vLLM, to benchmarking and safe teardown. It encodes hard-won details like the 10 GB boot disk overflow issue, invisible TPUS_PER_TPU_FAMILY quotas, and required vLLM flags (--tool-call-parser gemma4, --disable_chunked_mm_input), and includes a self-hosted log triage tool where Gemma 4 analyzes its own infrastructure logs.