{"slug":"didhd-sagemaker-deploy","source_name":"didhd/sagemaker-deploy","name":"Didhd/Sagemaker Deploy","description":"Deploy an open-weight LLM to a SageMaker AI real-time endpoint as an Inference Component, using the latest vLLM Deep Learning Container, a GPU instance sized to the model, tensor-parallel set to the GPU count, and model weights staged in S3. Use when the user asks to deploy / host / serve an open-weight model (e.g. GPT-OSS-20B) on SageMaker for inference or benchmarking. Works for any HuggingFace SafeTensor model the vLLM container supports — nothing here is model-specific.","version":1,"lift":{"pass_rate_delta_pts":40.91,"pass_rate_pct":81.8,"total_cases":22,"passed_cases":18,"tokens_delta_pct":33.1,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-03T08:59:20.771594+00:00"},"skill_score":0.8182,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":40.91,"with_pass_pct":81.8,"without_pass_pct":40.9,"tokens_delta_pct":33.1,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":19,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-03T08:59:20.771594+00:00","run_id":"7f578608-261f-474a-9785-bf62755a5ad3","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":"Apache-2.0","install_count":0,"manifest_hash":"1b581e5b85cf83bad7810fad461b2467ec6bbbe29022cdc098408a05aec86211","raw_url":"https://app.decimal.ai/s/didhd-sagemaker-deploy/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/didhd-sagemaker-deploy"}