{"slug":"majiayu000-ai-llm-inference","source_name":"majiayu000/ai-llm-inference","name":"Majiayu000/AI LLM Inference","description":"Operational patterns for LLM inference: latency budgeting, tail-latency control, caching, batching/scheduling, quantization/compression, parallelism, and reliable serving at scale. Emphasizes production-grade performance, cost control, and observability.","version":1,"lift":{"pass_rate_delta_pts":4.17,"pass_rate_pct":91.7,"total_cases":24,"passed_cases":22,"tokens_delta_pct":119.6,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-09-03T21:04:53.945486+00:00"},"skill_score":0.9167,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":4.17,"with_pass_pct":91.7,"without_pass_pct":87.5,"tokens_delta_pct":119.6,"turns_delta_pct":0,"total_cases":24,"cases_aggregated":24,"verdict":"mixed","never_hurt":true,"completed_at":"2026-09-03T21:04:53.945486+00:00","run_id":"fdfe99f1-777f-4b13-87d5-cc799ab716f6","latest_attempt":{"id":"fdfe99f1-777f-4b13-87d5-cc799ab716f6","runner_model":"gemini-3.6-flash","overall_verdict":"mixed","completed_at":"2026-09-03T21:04:53.945486+00:00","gate":null},"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,"total_uses":0,"total_users":0,"manifest_hash":"346247c25ebb1dcc4804f58e373643d0151d13a6abc39f8b009f5c2437c9d679","install_name":"majiayu000-ai-llm-inference","version_id":"e3295ec9-a1ec-41f4-9b43-adecce08e117","body_sha256":"346247c25ebb1dcc4804f58e373643d0151d13a6abc39f8b009f5c2437c9d679","render_hash":"bd8e96bfa221f18d6087196aee76c5e59d7fb00291bb2600381ef89cb4e0a926","raw_url":"https://app.decimal.ai/s/majiayu000-ai-llm-inference/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/majiayu000-ai-llm-inference"}