PulseAugur
EN
LIVE 18:57:37

MLC enables running large models on browsers, iPhones, and AMD cards

By PulseAugur Editorial · [8 sources] ·

The Machine Learning Compilation (MLC) group, led by Tianqi Chen at CMU, is developing frameworks like MLC Chat and Web LLM to enable running large language models on consumer hardware, including iPhones and web browsers. This initiative aims to mitigate the current GPU shortage by allowing models to run locally on devices with AMD cards or even just CPUs. Projects like Hugging Face's text-to-webapp generator and Gradio are also contributing to easier deployment and accessibility of ML models for developers and end-users. AI

RANK_REASON This cluster discusses research and development in ML compilation frameworks and tools for broader accessibility, rather than a specific frontier model release or major industry shift.

Read on Practical AI →

AI-generated summary · Google Gemini · from 8 sources. How we write summaries →

MLC enables running large models on browsers, iPhones, and AMD cards

COVERAGE [8]

  1. Hugging Face Blog TIER_1 English(EN) ·

    Making a web app generator with open ML models

  2. Eugene Yan TIER_1 English(EN) ·

    39 Lessons on Building ML Systems, Scaling, Execution, and More

    ML systems, production & scaling, execution & collaboration, building for users, conference etiquette.

  3. Eugene Yan TIER_1 English(EN) ·

    The Data Scientist Show - Building end-to-end ML systems

    Daliana and I had a 2hr chat on all things data science and machine learning.

  4. Eugene Yan TIER_1 English(EN) ·

    DataTalksClub - Building an ML System; Behind the Scenes

    Design and architecture, tech stack, methodology, results, and lessons learned.

  5. Latent Space Podcast TIER_1 English(EN) · Tianqi Chen ·

    LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML

    <p><em>We have just announced our first set of speakers at </em><a href="https://www.ai.engineer/summit" target="_blank"><em>AI Engineer Summit</em></a><em>! Sign up for the livestream or email </em><a href="http://[email protected]" target="_blank"><em>[email protected]</e…

  6. Practical AI TIER_1 English(EN) · Practical AI LLC ·

    Quick, beautiful web UIs for ML apps

    <p>Abubakar Abid joins Daniel and Chris for a tour of <a href="https://www.gradio.app">Gradio</a> and tells them about the project joining Hugging Face. What’s Gradio? The fastest way to demo your machine learning model with a friendly web interface, allowing non-technical users …

  7. Practical AI TIER_1 English(EN) · Practical AI LLC ·

    The fastest way to build ML-powered apps

    <p>Tuhin Srivastava tells Daniel and Chris why <a href="https://www.baseten.co">BaseTen</a> is <em>the</em> application development toolkit for data scientists. BaseTen’s goal is to make it simple to serve machine learning models, write custom business logic around them, and expo…

  8. Practical AI TIER_1 English(EN) · Practical AI LLC ·

    Accelerating ML innovation at MLCommons

    <p>MLCommons launched in December 2020 as an open engineering consortium that seeks to accelerate machine learning innovation and broaden access to this critical technology for the public good. David Kanter, the executive director of MLCommons, joins us to discuss the launch and …

RELATED ENTITIES

RELATED TOPICS