{"article":{"annotation":{"article_id":"aws-llama-cpp-decision-models-sagemaker-2026","available_at":"2026-10-15T21:30:29.900620Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"8a7e532367c7d6d78dbe61649f42365f42512638fd9e129aeefd25ee0c5ec1aa","input_sha256":"f9334e4498d00fcd2291c870ab817b9610ab0357615fa032590f875114f8ee8d","limitations":["Rule-derived subjects are candidates, not verified editorial labels or calibrated model probabilities.","Coverage is distinct from event location. Unknown country/city/coordinates remain absent; no automatic geocoding.","Article geometries keep their stated precision and methodology; reproducing them is not independent coordinate verification."],"method":"controlled-rules-v1","places":[],"rules_sha256":"fb5ad3c27c91cb840f7a0a05f7f64a5cb26ad0374409ff9457f277c7092e22b4","schema_version":1,"subjects":[{"concept_id":"medtop:20001298","confidence":null,"confidence_method":null,"evidence":[{"field":"en.title+en.summary","language":"en","note":"Subject suggested from the title or summary: AI","source_urls":["https://aws.amazon.com/blogs/machine-learning/deploy-decision-models-with-llama-cpp-on-amazon-sagemaker-ai/"]}],"method":"controlled-rules-v1","rule_id":"artificial-intelligence","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=pt","category":"technology","content":{"key_points":[],"paragraphs":["Um guia da AWS de 12 de outubro explica como servir um modelo GGUF no SageMaker AI com o contêiner Deep Learning padrão e gerar respostas compatíveis com OpenAI. Inclui opções de CPU e GPU.","Um adaptador SemIf opcional retorna probabilidades para opções declaradas. Como o llama-server não expõe logits nem estado do modelo, o caminho SemIf cria uma imagem derivada com CodeBuild. O texto é um guia de implantação, não uma comparação independente."],"sections":[]},"corrections":[],"country":null,"data":{"blocks":[{"description":{"ar":"AWS تشغّل نماذج القرار باستخدام llama.cpp على SageMaker","de":"AWS stellt Entscheidungsmodelle mit llama.cpp auf SageMaker bereit","en":"AWS serves decision models with llama.cpp on SageMaker","es":"AWS ejecuta modelos de decisión con llama.cpp en SageMaker","fr":"AWS déploie des modèles de décision avec llama.cpp sur SageMaker","pt":"AWS executa modelos de decisão com llama.cpp no SageMaker","tr":"AWS, llama.cpp ile SageMaker’da karar modellerini sunuyor"},"id":"reported-event","items":[{"date":"2026-10-12","description":{"ar":"يشرح دليل AWS المؤرخ في 12 أكتوبر تشغيل نموذج GGUF عبر نقطة نهاية SageMaker AI باستخدام حاوية Deep Learning القياسية، مع ردود متوافقة مع OpenAI. ويتضمن خيارات نشر على CPU وGPU.","de":"Ein AWS-Leitfaden vom 12. Oktober beschreibt, wie ein GGUF-Modell mit dem standardmäßigen Deep-Learning-Container über SageMaker AI OpenAI-kompatible Antworten liefert. Er umfasst CPU und GPU.","en":"An AWS guide dated October 12 explains serving a GGUF model through a SageMaker AI endpoint using the standard Deep Learning Container, returning OpenAI-compatible chat responses. It includes CPU and GPU deployment options.","es":"Una guía de AWS del 12 de octubre explica cómo servir un modelo GGUF en SageMaker AI con el contenedor Deep Learning estándar y obtener respuestas compatibles con OpenAI. Incluye opciones de CPU y GPU.","fr":"Un guide AWS du 12 octobre décrit le service d’un modèle GGUF via un point de terminaison SageMaker AI avec le conteneur Deep Learning standard, produisant des réponses compatibles avec OpenAI. Il propose CPU et GPU.","pt":"Um guia da AWS de 12 de outubro explica como servir um modelo GGUF no SageMaker AI com o contêiner Deep Learning padrão e gerar respostas compatíveis com OpenAI. Inclui opções de CPU e GPU.","tr":"12 Ekim tarihli AWS rehberi, GGUF modelini standart Deep Learning Container ile SageMaker AI uç noktasında çalıştırıp OpenAI uyumlu sohbet yanıtları almayı anlatıyor. Örnek CPU ve GPU dağıtım seçeneklerini içeriyor."},"label":{"ar":"تاريخ النشر","de":"Veröffentlichungsdatum","en":"Publication date","es":"Fecha de publicación","fr":"Date de publication","pt":"Data de publicação","tr":"Yayın tarihi"},"status":"occurred"}],"methodology":{"ar":"نُقل النطاق والقيم كما أوردها المصدر؛ وليس ذلك تحققاً مستقلاً.","de":"Umfang und Werte stammen aus der Quelle; keine unabhängige Prüfung.","en":"Scope and values are reported by the source; this is not independent verification.","es":"Alcance y cifras según la fuente; sin verificación independiente.","fr":"Périmètre et valeurs rapportés par la source ; sans vérification indépendante.","pt":"Escopo e valores segundo a fonte; sem verificação independente.","tr":"Kaynağın bildirdiği kapsam ve değerler aktarılmıştır; bağımsız doğrulama değildir."},"sourceUrls":["https://aws.amazon.com/blogs/machine-learning/deploy-decision-models-with-llama-cpp-on-amazon-sagemaker-ai/"],"title":{"ar":"AWS تشغّل نماذج القرار باستخدام llama.cpp على SageMaker","de":"AWS stellt Entscheidungsmodelle mit llama.cpp auf SageMaker bereit","en":"AWS serves decision models with llama.cpp on SageMaker","es":"AWS ejecuta modelos de decisión con llama.cpp en SageMaker","fr":"AWS déploie des modèles de décision avec llama.cpp sur SageMaker","pt":"AWS executa modelos de decisão com llama.cpp no SageMaker","tr":"AWS, llama.cpp ile SageMaker’da karar modellerini sunuyor"},"type":"events","updatedAt":"2026-10-15T21:22:42+00:00"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026/data/reported-event?lang=pt&format=csv","json":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026/data/reported-event?lang=pt&format=json"},"id":"reported-event"}],"data_types":["events"],"editorial_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"topic","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"event_id":"event-54ba4911-1bfd-5de8-8db3-8528a1d9636c","event_period":"2026-10-12","event_period_basis":"source-review","id":"aws-llama-cpp-decision-models-sagemaker-2026","image":null,"importance":0.6,"language":"pt","modified_at":"2026-10-15T21:30:20+00:00","publication_basis":"publication-record","published_at":"2026-10-15T21:30:20+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Ilustração conceitual de tecnologia, processadores e informações conectadas.","asset_id":"newsverum-v1-technology","avif_variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.avif","width":480},{"height":480,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-720.avif","width":720},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.avif","width":960},{"height":800,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1200.avif","width":1200},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.avif","width":1536}],"credit":"Newsverum","documentary":false,"height":1024,"kind":"symbolic-editorial-illustration","language":"pt","scope":"section","url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","variants":[{"height":320,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-480.webp","width":480},{"height":640,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-960.webp","width":960},{"height":1024,"url":"https://newsverum.com/assets/newsverum/illustrations/v1/technology-1536.webp","width":1536}],"width":1536},"slug":"aws-llama-cpp-decision-models-sagemaker-2026","sources":[{"checkedAt":"2026-10-15","name":"AWS","publishedAt":"2026-10-12","url":"https://aws.amazon.com/blogs/machine-learning/deploy-decision-models-with-llama-cpp-on-amazon-sagemaker-ai/"}],"summary":"Um guia da AWS de 12 de outubro explica como servir um modelo GGUF no SageMaker AI com o contêiner Deep Learning padrão e gerar respostas compatíveis com OpenAI. Inclui opções de CPU e GPU.","text":"Um guia da AWS de 12 de outubro explica como servir um modelo GGUF no SageMaker AI com o contêiner Deep Learning padrão e gerar respostas compatíveis com OpenAI. Inclui opções de CPU e GPU.\n\nUm guia da AWS de 12 de outubro explica como servir um modelo GGUF no SageMaker AI com o contêiner Deep Learning padrão e gerar respostas compatíveis com OpenAI. Inclui opções de CPU e GPU.\n\nUm adaptador SemIf opcional retorna probabilidades para opções declaradas. Como o llama-server não expõe logits nem estado do modelo, o caminho SemIf cria uma imagem derivada com CodeBuild. O texto é um guia de implantação, não uma comparação independente.","title":"AWS executa modelos de decisão com llama.cpp no SageMaker","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=en","language":"en","url":"https://newsverum.com/en/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=es","language":"es","url":"https://newsverum.com/es/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=de","language":"de","url":"https://newsverum.com/de/news/aws-llama-cpp-decision-models-sagemaker-2026"},{"api_url":"https://newsverum.com/api/v1/articles/aws-llama-cpp-decision-models-sagemaker-2026?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/aws-llama-cpp-decision-models-sagemaker-2026"}],"url":"https://newsverum.com/pt/news/aws-llama-cpp-decision-models-sagemaker-2026"},"version":"1"}