Maintenance in progress: we are indexing a large batch of new skills. Some pages may load slowly or briefly show no results. Nothing is lost, and everything is back to normal within the hour.
Profile My skills Saved Collections Edit profile Submit a skill

Ops LLM

Local LLM health checks and cache management. Probe Ollama/vLLM/SGLang endpoints, clean model caches.

majiayu000 7225fd9 2 files · 1.9 KB Updated 567 repo stars
AI & ML

File contents

LLM Ops

Manage local LLM runtimes and caches.

Commands

# Check all common LLM endpoints (Ollama, vLLM, SGLang)
./scripts/health.sh

# Check specific endpoint
./scripts/health.sh --target ollama:http://127.0.0.1:11434

# Continue even if some fail
./scripts/health.sh --warn-only

# Show cache sizes (dry-run)
./scripts/cache-clean.sh

# Actually clean caches
./scripts/cache-clean.sh --execute

# Clean additional path
./scripts/cache-clean.sh --path ~/.cache/torch --execute

Default Endpoints Checked

  • Ollama: http://127.0.0.1:11434
  • vLLM: http://127.0.0.1:8000
  • SGLang: http://127.0.0.1:30000

Default Cache Directories

  • ~/.cache/ollama
  • ~/.cache/huggingface
  • ~/.cache/vllm

Environment Variables

Variable Default Description
LLM_HEALTH_TIMEOUT 2 Seconds to wait per endpoint
LLM_CACHE_DIRS (see above) Space-separated cache paths

majiayu000/claude-skill-registry-data/tree/main/data/ops-llm commit 7225fd9407

Browse category

Frequently asked questions

npx skillmds add majiayu000/ops-llm