{"slug":"agentsope-agentsop-vllm","source_name":"agentsope/agentsop-vllm","name":"Agentsope/Agentsop Vllm","description":"Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.","version":1,"lift":{"pass_rate_delta_pts":15.38,"pass_rate_pct":96.2,"total_cases":26,"passed_cases":25,"tokens_delta_pct":308,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-24T14:17:20.220180+00:00"},"skill_score":0.9615,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":15.38,"with_pass_pct":96.2,"without_pass_pct":80.8,"tokens_delta_pct":308,"turns_delta_pct":0,"total_cases":26,"cases_aggregated":25,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-24T14:17:20.220180+00:00","run_id":"735944a6-6f21-42d9-8f95-3f33fc34add5","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"1b19ea458bd60542fae97afe8dbf196402454936e26c46f51f423e6e3f940e1c","raw_url":"https://app.decimal.ai/s/agentsope-agentsop-vllm/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/agentsope-agentsop-vllm"}