ExecuTorch Integrations

Facebook stands as the biggest social networking platform globally. We develop technologies that enable individuals to engage with their friends and family, discover communities, and expand their businesses. Inspired by the remarkable ways in which people support one another during challenging times, we see examples ranging from fundraising efforts to lifesaving assistance shared in posts or through blood donation sign-ups. The Facebook app simplifies the process of connecting with loved ones and finding new acquaintances, thanks to features such as Groups, Watch, and Marketplace that cater to shared interests. These tools not only foster personal connections but also create opportunities for communal growth and support.

WhatsApp offers a messaging platform that is fast, straightforward, secure, and free*, accessible on mobile devices globally. Designed with small business owners in mind, WhatsApp Business is available for download at no cost, allowing users to create catalogs that highlight their products and services. Furthermore, it provides tools that facilitate easy communication with customers by automating responses, sorting messages, and enabling quick replies. In addition to supporting small enterprises, WhatsApp also assists medium and large businesses in delivering customer support and crucial notifications. To discover more about the WhatsApp Business API, you can visit their website. Privacy is a priority on WhatsApp, which is why our latest app versions feature end-to-end encryption, ensuring that your most intimate conversations remain confidential. With this security measure, only you and your conversation partner can access your messages and calls, safeguarding them from interception by anyone else, including WhatsApp itself. This commitment to security reinforces our dedication to maintaining your privacy while you connect with others.

We prioritize people and emphasize craftsmanship and simplicity in everything we do. Our teams spark creativity globally, enabling over 1 billion individuals to create and share content. You can download the Instagram logo and other materials for use on your website, store displays, or various marketing efforts. By tapping into the passions of your audience, you can build stronger connections with your brand both online and offline. Share your narrative using distinct creative tools and engaging formats that motivate action. By fostering connections with new customers and enhancing relationships with current ones, you can grow your business effectively. From large corporations to local businesses, companies worldwide are achieving remarkable outcomes with Instagram. Engage with your followers through live streaming or showcase your products during live video sessions. Explore videos from your favorite creators and find fresh content through Instagram Video and Reels. Delve into a world of inspiration with photos and videos from new accounts in the Explore section, where you can also discover brands and small businesses that align with your personal style. Additionally, shopping for products that resonate with your aesthetic has never been easier on Instagram.

Kotlin is designed for ease of use, allowing you to develop robust applications right from the start. It seamlessly integrates with the Java ecosystem, enabling you to leverage your preferred JVM frameworks and libraries. You can share your application logic across web, mobile, and desktop platforms while ensuring a native experience for users. This approach not only saves time but also provides unlimited access to platform-specific features. Kotlin boasts strong community support and a rapidly expanding global network of contributors. With an extensive ecosystem filled with various community libraries, assistance is readily available—whether through community resources or direct inquiries to the Kotlin team. For mobile app development on both iOS and Android, Kotlin Multiplatform Mobile serves as an SDK, merging the advantages of cross-platform and native application creation. By maintaining a unified codebase for essential components like networking, data storage, and analytics, you can streamline the development process for your Android and iOS applications. This ultimately enhances productivity and fosters innovation in your projects.

Engaging in Swift programming is both enjoyable and interactive, as its syntax is not only concise but also highly expressive, incorporating modern features that developers appreciate. Designed with safety in mind, Swift enables the creation of software that operates at remarkable speeds. This programming language is the culmination of cutting-edge research into language design, paired with extensive experience in developing for Apple platforms. The use of named parameters is facilitated by a clear syntax, enhancing the readability and maintainability of APIs in Swift. A noteworthy convenience is the omission of semi-colons, allowing for a more streamlined coding experience. Additionally, inferred types contribute to a cleaner codebase and reduce the likelihood of errors, while modules eliminate the need for headers and create organized namespaces. To effectively cater to various international languages and even emojis, Swift strings are Unicode-compliant and utilize a UTF-8 encoding for optimized performance across diverse applications. Moreover, writing concurrent code becomes straightforward with intuitive built-in keywords that delineate asynchronous behavior, enhancing both code clarity and reliability. This combination of features makes Swift an appealing choice for developers aiming to create efficient and robust applications.

The latest iteration of the open-source AI model, which can be fine-tuned and deployed in various environments, is now offered in multiple versions, including 1B, 3B, 11B, and 90B, alongside the option to continue utilizing Llama 3.1. Llama 3.2 comprises a series of large language models (LLMs) that come pretrained and fine-tuned in 1B and 3B configurations for multilingual text only, while the 11B and 90B models accommodate both text and image inputs, producing text outputs. With this new release, you can create highly effective and efficient applications tailored to your needs. For on-device applications, such as summarizing phone discussions or accessing calendar tools, the 1B or 3B models are ideal choices. Meanwhile, the 11B or 90B models excel in image-related tasks, enabling you to transform existing images or extract additional information from images of your environment. Overall, this diverse range of models allows developers to explore innovative use cases across various domains.

LLaVA, or Large Language-and-Vision Assistant, represents a groundbreaking multimodal model that combines a vision encoder with the Vicuna language model, enabling enhanced understanding of both visual and textual information. By employing end-to-end training, LLaVA showcases remarkable conversational abilities, mirroring the multimodal features found in models such as GPT-4. Significantly, LLaVA-1.5 has reached cutting-edge performance on 11 different benchmarks, leveraging publicly accessible data and achieving completion of its training in about one day on a single 8-A100 node, outperforming approaches that depend on massive datasets. The model's development included the construction of a multimodal instruction-following dataset, which was produced using a language-only variant of GPT-4. This dataset consists of 158,000 distinct language-image instruction-following examples, featuring dialogues, intricate descriptions, and advanced reasoning challenges. Such a comprehensive dataset has played a crucial role in equipping LLaVA to handle a diverse range of tasks related to vision and language with great efficiency. In essence, LLaVA not only enhances the interaction between visual and textual modalities but also sets a new benchmark in the field of multimodal AI.

Qwen3 is a state-of-the-art large language model designed to revolutionize the way we interact with AI. Featuring both thinking and non-thinking modes, Qwen3 allows users to customize its response style, ensuring optimal performance for both complex reasoning tasks and quick inquiries. With the ability to support 119 languages, the model is suitable for international projects. The model's hybrid training approach, which involves over 36 trillion tokens, ensures accuracy across a variety of disciplines, from coding to STEM problems. Its integration with platforms such as Hugging Face, ModelScope, and Kaggle allows for easy adoption in both research and production environments. By enhancing multilingual support and incorporating advanced AI techniques, Qwen3 is designed to push the boundaries of AI-driven applications.

Effortlessly switch between eager and graph modes using TorchScript, while accelerating your journey to production with TorchServe. The torch-distributed backend facilitates scalable distributed training and enhances performance optimization for both research and production environments. A comprehensive suite of tools and libraries enriches the PyTorch ecosystem, supporting development across fields like computer vision and natural language processing. Additionally, PyTorch is compatible with major cloud platforms, simplifying development processes and enabling seamless scaling. You can easily choose your preferences and execute the installation command. The stable version signifies the most recently tested and endorsed iteration of PyTorch, which is typically adequate for a broad range of users. For those seeking the cutting-edge, a preview is offered, featuring the latest nightly builds of version 1.10, although these may not be fully tested or supported. It is crucial to verify that you meet all prerequisites, such as having numpy installed, based on your selected package manager. Anaconda is highly recommended as the package manager of choice, as it effectively installs all necessary dependencies, ensuring a smooth installation experience for users. This comprehensive approach not only enhances productivity but also ensures a robust foundation for development.

Objective-C serves as the primary programming language for developing applications on both OS X and iOS platforms. As an extension of the C programming language, it offers robust object-oriented features alongside a dynamic runtime environment. The language retains the syntax, basic types, and control flow statements of C, while introducing additional syntax for class and method definitions. Furthermore, it enhances language capabilities with built-in support for managing object graphs and utilizing object literals, allowing for dynamic typing and binding that defers many tasks until runtime. While creating applications for OS X or iOS, developers predominantly engage with objects, which are instances of Objective-C classes; some are provided by frameworks like Cocoa or Cocoa Touch, while others are custom-built by the developer. Ultimately, mastering Objective-C can significantly improve your ability to create sophisticated and efficient applications for Apple’s platforms.

C++ is known for its straightforward and lucid syntax. While a novice programmer might find C++ somewhat more obscure than other languages due to its frequent use of special symbols (like {}[]*&!|...), understanding these symbols can actually enhance clarity and structure, making it more organized than languages that depend heavily on verbose English syntax. Additionally, the input/output system of C++ has been streamlined compared to C, and the inclusion of the standard template library facilitates data handling and communication, making it as user-friendly as other programming languages without sacrificing functionality. This language embraces an object-oriented programming paradigm, viewing software components as individual objects with distinct properties and behaviors, which serves to enhance or even replace the traditional structured programming approach that primarily centered around procedures and parameters. Ultimately, this focus on objects allows for greater flexibility and scalability in software development.

Whisper is a powerful speech-to-text model created by OpenAI to deliver accurate and reliable audio transcription. It is trained on a large dataset of 680,000 hours of multilingual audio, making it highly robust across different languages and environments. The model performs multiple tasks, including transcription, translation, and language detection within a single system. Whisper uses a Transformer-based encoder-decoder architecture to process audio converted into log-Mel spectrograms. It can generate phrase-level timestamps and handle noisy or complex audio inputs effectively. Unlike many specialized models, Whisper is designed for strong zero-shot performance across diverse datasets. It supports multilingual transcription and can translate speech from various languages into English. The model is open-sourced, allowing developers and researchers to build and customize applications بسهولة. Its flexibility makes it suitable for use cases like voice assistants, transcription services, and accessibility tools. Overall, Whisper provides a scalable and versatile foundation for speech processing applications.

Phi-4-mini-reasoning is a transformer-based language model with 3.8 billion parameters, specifically designed to excel in mathematical reasoning and methodical problem-solving within environments that have limited computational capacity or latency constraints. Its optimization stems from fine-tuning with synthetic data produced by the DeepSeek-R1 model, striking a balance between efficiency and sophisticated reasoning capabilities. With training that encompasses over one million varied math problems, ranging in complexity from middle school to Ph.D. level, Phi-4-mini-reasoning demonstrates superior performance to its base model in generating lengthy sentences across multiple assessments and outshines larger counterparts such as OpenThinker-7B, Llama-3.2-3B-instruct, and DeepSeek-R1. Equipped with a 128K-token context window, it also facilitates function calling, which allows for seamless integration with various external tools and APIs. Moreover, Phi-4-mini-reasoning can be quantized through the Microsoft Olive or Apple MLX Framework, enabling its deployment on a variety of edge devices, including IoT gadgets, laptops, and smartphones. Its design not only enhances user accessibility but also expands the potential for innovative applications in mathematical fields.

Voxtral models represent cutting-edge open-source systems designed for speech understanding, available in two sizes: a larger 24 B variant aimed at production-scale use and a smaller 3 B variant suitable for local and edge applications, both of which are provided under the Apache 2.0 license. These models excel in delivering precise transcription while featuring inherent semantic comprehension, accommodating long-form contexts of up to 32 K tokens and incorporating built-in question-and-answer capabilities along with structured summarization. They automatically detect languages across a range of major tongues and enable direct function-calling to activate backend workflows through voice commands. Retaining the textual strengths of their Mistral Small 3.1 architecture, Voxtral can process audio inputs of up to 30 minutes for transcription tasks and up to 40 minutes for comprehension, consistently surpassing both open-source and proprietary competitors in benchmarks like LibriSpeech, Mozilla Common Voice, and FLEURS. Users can access Voxtral through downloads on Hugging Face, API endpoints, or by utilizing private on-premises deployments, and the model also provides options for domain-specific fine-tuning along with advanced features tailored for enterprise needs, thus enhancing its applicability across various sectors.