{"article":{"annotation":{"article_id":"intel-inference-microservices-xeon-llm","available_at":"2026-10-15T09:48:47.872058Z","geography_revision":"ef6ee0010dda5fe7b240fd514749b43e214c57da73222d2e40ec83b276dd0977","id":"bef2f16b796d39bcedb1bcc0c35b3c5d970236bda2bb09188ae788c9138d948b","input_sha256":"f454a6ed74efb8923697b488d8889a8d49f87081dd4a7fe218b21800fea34c8c","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":[{"admin1":null,"city":null,"coordinate_note":null,"coordinate_reference_system":"OGC:CRS84","coordinate_source":null,"country":"US","evidence":[{"field":"country","language":"en","note":"Explicit preserved editorial country/region; no city or national centroid inferred","source_urls":["https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-inference-microservices-tuned-llm-processors.html"]}],"geometry":null,"id":"iso3166-1:US","kind":"country-or-area","labels":{"ar":"الولايات المتحدة الأمريكية","en":"United States of America","es":"Estados Unidos de América","fr":"États-Unis d’Amérique"},"match_status":"candidate","precision":"regional","role":"coverage","uncertainty_m":null}],"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: LLM","source_urls":["https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-inference-microservices-tuned-llm-processors.html"]}],"method":"controlled-rules-v1","rule_id":"artificial-intelligence","status":"candidate"},{"concept_id":"medtop:20000225","confidence":null,"confidence_method":null,"evidence":[{"field":"en.title+en.summary","language":"en","note":"Subject suggested from the title or summary: software","source_urls":["https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-inference-microservices-tuned-llm-processors.html"]}],"method":"controlled-rules-v1","rule_id":"computing-it","status":"candidate"}],"taxonomy_revision":"1f2db31d811fca07e99b16d402c10e2cc2965c9df1c7b41d9be348b40a24e7fb","taxonomy_version":"IPTC Media Topics 2026-Q2"},"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=es","category":"technology","content":{"key_points":[],"paragraphs":["La primera versión funciona con vLLM en BF16 sobre Xeon de 4.ª, 5.ª y 6.ª generación; Intel recomienda 32 GB de RAM. La empresa dice que los perfiles ajustan precisión, distribución entre núcleos y disposición de memoria, según pruebas propias en hardware.","Intel afirma que el software se ejecuta localmente, sin endpoint alojado ni clave de API, y que las aplicaciones pueden usar la interfaz estándar cambiando la URL base. El soporte para GPU, otros motores, gráficos Helm y un operador de Kubernetes está previsto para el futuro, no en esta versión."],"sections":[]},"corrections":[],"country":"US","data":{"blocks":[{"description":{"ar":"أطلقت إنتل برنامج استدلال للنماذج اللغوية باستخدام حاويات مضبوطة لكل نموذج على معالجات Xeon.","de":"Intel veröffentlichte LLM-Inferenzsoftware mit modellbezogen optimierten Containern für Xeon-Prozessoren.","en":"Intel released LLM inference software using per-model tuned containers on Xeon processors.","es":"Intel publicó software de inferencia LLM con contenedores ajustados por modelo en procesadores Xeon.","fr":"Intel a publié un logiciel d’inférence LLM utilisant des conteneurs réglés par modèle sur processeurs Xeon.","pt":"A Intel lançou software de inferência LLM com contêineres ajustados por modelo em processadores Xeon.","tr":"Intel, Xeon işlemciler üzerinde model başına ayarlanmış konteynerlerle LLM çıkarım yazılımını yayımladı."},"id":"announcement","items":[{"date":"2026-10-14","description":{"ar":"أطلقت إنتل برنامج استدلال للنماذج اللغوية باستخدام حاويات مضبوطة لكل نموذج على معالجات Xeon.","de":"Intel veröffentlichte LLM-Inferenzsoftware mit modellbezogen optimierten Containern für Xeon-Prozessoren.","en":"Intel released LLM inference software using per-model tuned containers on Xeon processors.","es":"Intel publicó software de inferencia LLM con contenedores ajustados por modelo en procesadores Xeon.","fr":"Intel a publié un logiciel d’inférence LLM utilisant des conteneurs réglés par modèle sur processeurs Xeon.","pt":"A Intel lançou software de inferência LLM com contêineres ajustados por modelo em processadores Xeon.","tr":"Intel, Xeon işlemciler üzerinde model başına ayarlanmış konteynerlerle LLM çıkarım yazılımını yayımladı."},"label":{"ar":"إنتل تطلق خدمات مصغرة لاستدلال النماذج اللغوية على Xeon","de":"Intel stellt Inference Microservices für LLM-Inferenz auf Xeon vor","en":"Intel introduces Inference Microservices for LLM serving on Xeon","es":"Intel presenta Inference Microservices para inferencia de modelos en Xeon","fr":"Intel présente Inference Microservices pour l’inférence de modèles sur Xeon","pt":"Intel apresenta Inference Microservices para inferência de LLM em Xeon","tr":"Intel, Xeon üzerinde LLM çıkarımı için Inference Microservices’i tanıttı"},"status":"occurred"}],"methodology":{"ar":"الحدث إعلان إنتل البرمجي بتاريخ 14 أكتوبر 2026. نطاق المنتج وادعاءات التحقق من الإعدادات صادرة عن إنتل؛ ولم يقدم الإعلان نتائج معيار أداء مستقلة.","de":"Das Ereignis ist Intels Softwareankündigung vom 14. Oktober 2026. Produktumfang und Aussagen zu validierten Profilen stammen von Intel; unabhängige Benchmark-Ergebnisse enthält die Mitteilung nicht.","en":"The event is Intel’s software announcement dated October 14, 2026. Product scope and statements about validated tuning are Intel’s; the announcement provides no independent benchmark result.","es":"El evento es el anuncio de software de Intel del 14 de octubre de 2026. El alcance y las afirmaciones sobre perfiles validados provienen de Intel; el anuncio no ofrece resultados de referencia independientes.","fr":"L’événement est l’annonce logicielle d’Intel du 14 octobre 2026. Le périmètre du produit et les affirmations de validation des réglages viennent d’Intel; aucun benchmark indépendant n’est fourni.","pt":"O evento é o anúncio de software da Intel em 14 de outubro de 2026. O escopo do produto e as afirmações sobre perfis validados são da Intel; o anúncio não apresenta benchmark independente.","tr":"Olay, Intel’in 14 Ekim 2026 tarihli yazılım duyurusudur. Ürün kapsamı ve ayarların doğrulandığına ilişkin ifadeler Intel’e aittir; duyuruda bağımsız kıyaslama sonucu sunulmamıştır."},"sourceUrls":["https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-inference-microservices-tuned-llm-processors.html"],"title":{"ar":"إصدار برمجي من إنتل","de":"Intel-Softwareveröffentlichung","en":"Intel software release","es":"Versión de software de Intel","fr":"Version logicielle d’Intel","pt":"Lançamento de software da Intel","tr":"Intel yazılım sürümü"},"type":"events","updatedAt":"2026-10-15T09:12:39Z"}],"version":1},"data_downloads":[{"formats":{"csv":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm/data/announcement?lang=es&format=csv","json":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm/data/announcement?lang=es&format=json"},"id":"announcement"}],"data_types":["events"],"editorial_illustration":{"alt":"Ilustración conceptual de tecnología, procesadores e información conectada.","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":"es","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-0bc218f5-47fa-552b-9710-680671b5683d","event_period":"2026-10-14","event_period_basis":"event-or-reference-period","id":"intel-inference-microservices-xeon-llm","image":null,"importance":0.6,"language":"es","modified_at":"2026-10-15T09:48:29+00:00","publication_basis":"publication-record","published_at":"2026-10-15T09:48:29+00:00","reading_minutes":1,"region":"world","section_illustration":{"alt":"Ilustración conceptual de tecnología, procesadores e información conectada.","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":"es","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":"intel-inference-microservices-xeon-llm","sources":[{"checkedAt":"2026-10-15","name":"Intel","publishedAt":"2026-10-14","url":"https://www.intel.com/content/www/us/en/newsroom/news/artificial-intelligence/intel-inference-microservices-tuned-llm-processors.html"}],"summary":"Intel anunció software de microservicios en contenedores para servir modelos de lenguaje grandes en procesadores Xeon. Cada contenedor ofrece un modelo mediante una API compatible con OpenAI y detecta el procesador anfitrión al iniciarse para elegir el perfil validado por Intel para ese modelo y hardware.","text":"Intel anunció software de microservicios en contenedores para servir modelos de lenguaje grandes en procesadores Xeon. Cada contenedor ofrece un modelo mediante una API compatible con OpenAI y detecta el procesador anfitrión al iniciarse para elegir el perfil validado por Intel para ese modelo y hardware.\n\nLa primera versión funciona con vLLM en BF16 sobre Xeon de 4.ª, 5.ª y 6.ª generación; Intel recomienda 32 GB de RAM. La empresa dice que los perfiles ajustan precisión, distribución entre núcleos y disposición de memoria, según pruebas propias en hardware.\n\nIntel afirma que el software se ejecuta localmente, sin endpoint alojado ni clave de API, y que las aplicaciones pueden usar la interfaz estándar cambiando la URL base. El soporte para GPU, otros motores, gráficos Helm y un operador de Kubernetes está previsto para el futuro, no en esta versión.","title":"Intel presenta Inference Microservices para inferencia de modelos en Xeon","topics":[],"translations":[{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=tr","language":"tr","url":"https://newsverum.com/tr/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=en","language":"en","url":"https://newsverum.com/en/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=ar","language":"ar","url":"https://newsverum.com/ar/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=fr","language":"fr","url":"https://newsverum.com/fr/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=es","language":"es","url":"https://newsverum.com/es/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=de","language":"de","url":"https://newsverum.com/de/news/intel-inference-microservices-xeon-llm"},{"api_url":"https://newsverum.com/api/v1/articles/intel-inference-microservices-xeon-llm?lang=pt","language":"pt","url":"https://newsverum.com/pt/news/intel-inference-microservices-xeon-llm"}],"url":"https://newsverum.com/es/news/intel-inference-microservices-xeon-llm"},"version":"1"}