特色软件工具
英特尔® 发行版 OpenVINO™ 工具套件
运行 AI 推理、优化模型并跨多个平台部署。
英特尔® oneAPI 工具套件
异构架构为所有平台提供了统一的编程模型。
英特尔® Graphics Performance Analyzers
使用系统、跟踪和帧分析器识别和解决游戏中的性能问题。
英特尔® Quartus® Prime 设计软件
面向英特尔® FPGA、SoC 和复杂可编程逻辑器件 (CPLD) 的设计，从设计输入和综合，到优化、验证和模拟。
获取您的软件和开发产品
试用、购买或直接从英特尔和热门存储库下载。
探索我们的设计服务
在 11 天, 21 小时
Webinar: Use Local AI for Efficient LLM Inference
2025年4月16日 | 16:00
Build a large language model (LLM) application using the power of AI PC processing, tapping the native capabilities of Intel® Core™ Ultra processors for running AI locally. The session shows how to develop a Python* back end with a browser extension that compactly summarizes web page content. The exercise showcases the Intel® hardware and software that makes it possible to run LLMs locally.
April 16, 2025, 9:00 a.m. Pacific Daylight Time (PDT)
在 17 天, 21 小时
Workshop: Deploy Enterprise-Grade GenAI with OPEA on AWS*
2025年4月22日 | 16:00
Open Platform for Enterprise AI (OPEA) provides the building blocks for enterprise applications, including LLMs, prompt engines, and data stores, based on retrieval augmented generation (RAG) principles. This workshop guides you through the processes of building and deploying enterprise-grade generative AI (GenAI) applications for launching on Amazon Web Services (AWS)*. Explore the capabilities of OPEA to streamline development of a RAG pipeline using structured, repeatable techniques.
April 22, 2025, 9:00 a.m. – 12:00 p.m. Pacific Daylight Time (PDT)
在 18 天, 21 小时
Webinar: Power DeepSeek* Models and Applications on Intel® Hardware
2025年4月23日 | 16:00
Run DeepSeek* models on Intel® hardware to experience the advantages of open source freedom, advanced reasoning capabilities, and a lightweight footprint. This webinar uses the vLLM inferencing engine and the ChatQnA application to illustrate the essential qualities of DeepSeek. The session also demonstrates the low cost of running AI on the CPUs of Intel® Xeon® processors and Intel® Gaudi® AI accelerators, a clear alternative to GPUs that is efficient and cost-effective.
Gain familiarity with the Open Platform for Enterprise AI (OPEA), which is used to power the ChatQnA application and provides a useful tool to show the fundamentals of constructing chatbots. Developers viewing the tutorials provided can see how the DeepSeek models can be run on relatively modest hardware and get excited about the potential for running successfully on Intel hardware.
April 23, 2025, 9:00 a.m. Pacific Daylight Time (PDT)