{"content_coverage":{"reference_guide":false,"developer_starter":false,"integration_test":"not-run"},"schema_version":"1.0.0","type":"development-proposal","product_id":"industrial-api:TritonInferenceServer","name":"Triton Inference Server","provider":"NVIDIA","url":"https://smart-tools.ai/product/TritonInferenceServer","localized_urls":{"en":"https://smart-tools.ai/product/TritonInferenceServer","zh-TW":"https://smart-tools.ai/zh-tw/product/TritonInferenceServer"},"category":"edge","capability_id":"cap:edge-ai","technology_hub":"https://smart-tools.ai/industrial-ai/edge-ai","interface_kind":"API / SDK","deployment":"self-hosted","official_documentation":"https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html","sources":["https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html"],"source_review":{"level":"P1","status":"official-source-reviewed","checked_at":"2026-10-07"},"provider_summary":{"en":"Serve trained models through an inference-server interface.","zh-TW":"透過推論伺服器接口提供已訓練模型。"},"proposed_product":{"en":"Multi-model inference endpoint","zh-TW":"多模型推論接口"},"feasibility":{"tier":"integration","rationale":{"en":"Validate runtime, schemas or hardware together before estimating a deployable product.","zh-TW":"估算可交付產品前，需共同驗證執行環境、資料結構或硬體。"},"basis":"development-judgment;not-traffic-ranked"},"proposed_inputs":{"en":"One pinned model, representative inputs, target runtime and workload.","zh-TW":"一個鎖定版本的模型、代表性輸入、目標環境與工作量。"},"proposed_deliverable":{"en":"Predictions or deployment evidence with model version, latency and resource measurements.","zh-TW":"附模型版本、延遲與資源量測的預測或部署證據。"},"acceptance_criterion":{"en":"Verify outputs against a known sample and measure latency, memory and failed calls on the chosen target.","zh-TW":"用已知樣本驗證輸出，並在選定環境量測延遲、記憶體與失敗呼叫。"},"dependencies":{"en":"Model rights, supported operators, memory budget and hardware or serving infrastructure.","zh-TW":"模型使用權、支援的算子、記憶體預算與硬體或服務環境。"},"integration_condition":null,"proposed_adapter_envelope":{"provider":"NVIDIA","operation":"chosen-documented-operation","source_url":"https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html","captured_at":"ISO-8601 timestamp","status":"ok|pending|unknown|failed","data":"provider response mapped by the team","evidence":"source references","errors":"explicit error details"},"adapter_envelope_status":"proposed-internal-contract;not-a-provider-response","development_status":"concept-specification","integration_test":"not-run","pricing_status":"provider-terms-review-required","estimate_status":"requires-access-and-sample-validation","traffic_status":"not-measured-in-this-assessment","measurement_events":["product_view","product_to_docs","product_to_spec","bridge_to_industrial_ai"]}