AMD Developer Central
AMD Developer Central
  • 32
  • 5 063
Interview with Amandine Flachs - AMD Pervasive AI Developer Contest 2024 1st Prize in Gen AI
In this fireside chat, Prithvi Mattur, Product Marketing Manager in the AI Group at AMD, interviews Amandine Flachs, an AI Consultant who secured first prize in the Generative AI, AMD Instinct™ accelerators category at the AMD Pervasive AI Developer Contest 2024 for her team’s work on an AI Math Teacher that they named Mather.
Amandine shares her experience working with the AMD platform, the challenges faced during the contest, and her vision for scaling her project. She offers advice to fellow female AI developers, encouraging them to pursue their ideas and leverage available tools to push their projects further.
Learn more about Amandine’s winning project, Mather: www.hackster.io/515082/mather-your-llm-math-tutor-trained-on-amd-mi210-f59e14
Watch a video of Mather in action: th-cam.com/video/f3VZv3sJrVY/w-d-xo.html
Learn more about the hardware for Mather, AMD Instinct™ MI210 accelerators: www.amd.com/en/products/accelerators/instinct/mi200/mi210.html
The information contained in this video represents the view of AMD or the third-party presenter as of the date presented. AMD and/or the third-party presenters have no obligation to update any forward-looking content in the above presentations. AMD is not responsible for the content of any third-party presentations and does not necessarily endorse the comments made therein. GD-84.
Find the resources you need to develop using AMD products: www.amd.com/en/developer.html
***
© 2024 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, EPYC, ROCm, and AMD Instinct and combinations thereof are trademarks of Advanced Micro Devices, Inc.
มุมมอง: 220

วีดีโอ

MLCommons and MLPerf - Interview with Meena Arunachalam and Mahesh Balasubramanian
มุมมอง 1847 ชั่วโมงที่ผ่านมา
Join Mahesh Balasubramanian, Director of Product Marketing for Instinct™ and ROCm™ at AMD, and Meena Arunachalam, Fellow for AI Software Engineering at AMD, as they discuss the importance of MLCommons® and MLPerf® benchmarks in the AI industry. Hear how AMD is excelling in MLPerf 4.1 results and how their hardware and software solutions are driving advancements in AI, HPC, deep learning, and ma...
Interview with Kerin Lovett - AMD Pervasive AI Developer Contest 2024 1st Prize in Gen AI
มุมมอง 1927 ชั่วโมงที่ผ่านมา
In this fireside chat, Prithvi Mattur, Product Marketing Manager in the AI Group at AMD, interviews Kerin Lovett, the first-place winner in the Generative AI, AMD Radeon™ GPUs category of the AMD Developer Contest. Kerin, an artist, shares the inspiration behind her project, which draws from her children's play and the importance of hands-on learning. Hear how she utilized various open-source t...
ONNX and TurnkeyML - Interview with AMD Engineers, Victoria Godsoe and Krishna Sivakumar
มุมมอง 687 ชั่วโมงที่ผ่านมา
Join Victoria Godsoe, AMD Manager of AI Developer Enablement Engineering, and Krishna Sivakumar, AMD ML Software Engineer, for a brief discussion of TurnkeyML: a comprehensive framework developed in collaboration with the ONNX community which streamlines the process of ingesting any open-source PyTorch models, optimizing and executing them across a diverse set of hardware targets. Krishna provi...
The Evolution of PyTorch - Interview with Joe Spisak of Meta
มุมมอง 2297 ชั่วโมงที่ผ่านมา
Join Niles Burbank, Representative to the PyTorch Foundation from AMD, as he interviews Joe Spisak, Product Director for Generative AI at Meta, discussing the early days and the evolution of PyTorch. Joe describes how this open-source machine learning library has become a cornerstone in the AI community, supporting groundbreaking projects like ChatGPT and Stable Diffusion. He dives into the imp...
What Does OPEN Mean to You?
มุมมอง 4947 ชั่วโมงที่ผ่านมา
We asked developers, data scientists, software engineers, and AMD technical leaders what OPEN means at our inaugural developer event. This is how our community embraces open source-fostering collaboration, inclusivity, and the ability to leverage the best technology advancing innovation and creativity. Learn more about how AMD contributes to open-source development: www.amd.com/en/corporate/res...
Open Source in AI - Interview with Rajat Monga of Microsoft
มุมมอง 1147 ชั่วโมงที่ผ่านมา
Join Mahesh Balasubramanian, Director of Product Marketing for Instinct and ROCm at AMD, as he sits down with Rajat Monga from Microsoft, CVP for AI Frameworks. They explore the evolution of open source in the AI industry, from early days of publishing research papers to the impact of open software like TensorFlow, which Rajat created. Rajat shares his experiences from his time at Google, highl...
MLIR and IREE - Interview with Niles Burbank, Robert Suderman, and Ian Nordeng
มุมมอง 517 ชั่วโมงที่ผ่านมา
Join Niles Burbank, AMD Representative to the PyTorch Foundation, along with Software Development colleagues Ian Nordeng and Robert Suderman, as they discuss integrating MLIR and IREE into the PyTorch ecosystem. They share their journey with PyTorch, the motivation behind connecting these tools, and the benefits for developers and researchers. Explore how MLIR serves as an extensible compiler s...
Insights on PyTorch and AOTriton - Interview with Niles Burbank and Jeff Daily
มุมมอง 1707 ชั่วโมงที่ผ่านมา
Join Niles Burbank, AMD Representative for the PyTorch Foundation, as he holds an insightful conversation with Jeff Daily, Software Fellow at AMD, about the evolution of PyTorch and its integration with AMD technologies. The discussion highlights the role of Triton, a domain-specific language and compiler. With AOTriton, AMD has expanded the capabilities of Triton, transforming it into an ahead...
Optimizing AI Models - Interview with Quentin Anthony of Zyphra
มุมมอง 1627 ชั่วโมงที่ผ่านมา
In this video, Ronak Shah, Product Marketing Manager for AMD Instinct™, and Quentin Anthony, Model Training Lead from Zyphra, discuss the latest advancements in AI model optimization. Quentin details how Zyphra is revolutionizing personalized AI with user-specific weights for efficient model pipelines. He explains how hybrid state space models merge attention and Mamba blocks for high performan...
AMD ROCm™ Platform Installation
มุมมอง 2497 ชั่วโมงที่ผ่านมา
In this Quick Bytes segment, Peter Cross, AMD Technical Engineer and Principal Member of Technical Staff, walks you through the essentials of getting started with AMD ROCm™ software. Learn how to install AMD ROCm™ software on Ubuntu, including setting up DKMS kernel headers and modules, and downloading the AMDGPU installer. This video covers various AMD ROCm™ software libraries and tools, inclu...
Open Ecosystems - Interview with Raghotham Murthy of Meta
มุมมอง 837 ชั่วโมงที่ผ่านมา
Join Mahesh Balasubramanian, Product Marketing Lead for Instinct and ROCm at AMD, as he sits down with Raghotham Murthy, Lead Engineer for Llama OSS at Meta. The conversation goes into the importance of open ecosystems and how they drive innovation and collaboration in the tech industry. Raghotham shares his extensive experience working with open-source projects, from his early days at Facebook...
Interview with Dobrea Dan Marius - AMD Pervasive AI Developer Contest 2024 1st Prize in Robotics AI
มุมมอง 237 ชั่วโมงที่ผ่านมา
In this fireside chat, Privthi Mattur, Product Marketing Manager from the AMD AI Group at AMD, interviews Dobrea Dan Marius, the first-place winner in the Robotics AI category of the AMD Pervasive AI Developer Contest 2024. Dobrea, a professor at Gheorghe Asachi Technical University of Iasi, Romania, shares his journey working with AMD Kria™ hardware and developing innovative UAV technology. He...
AMD ROCm™ Software Offline Installer Creator
มุมมอง 1437 ชั่วโมงที่ผ่านมา
In this video, Matt Elliot, a Technical Marketing Engineer at AMD, walks you through the AMD ROCm™ Offline Installer Creator. This tool simplifies the installation of AMD ROCm™ software drivers and related tools in high-security and air-gapped environments. You'll learn how to review the documentation, ensure system prerequisites, and match the target system's Linux distribution. The video cove...
AMD Infinity Hub Introduction
มุมมอง 627 ชั่วโมงที่ผ่านมา
In this video, you'll learn how to leverage the AMD Infinity Hub for your HPC and AI projects. The AMD Infinity Hub offers a collection of advanced software containers and deployment guides, enabling researchers, scientists, and engineers to speed up their time to science. The video covers the main features of the Infinity Hub, including how to navigate the hub's landing page, utilize user guid...
Webinar - Fine Tuning Llama3 on AMD Radeon GPUs
มุมมอง 799 ชั่วโมงที่ผ่านมา
Webinar - Fine Tuning Llama3 on AMD Radeon GPUs
GDC 2024 - Post-mortem GPU crash analysis with AMD Radeon™ GPU Detective (RGD)
มุมมอง 509 ชั่วโมงที่ผ่านมา
GDC 2024 - Post-mortem GPU crash analysis with AMD Radeon™ GPU Detective (RGD)
GDC 2024 - Shader Instrumentation with GPU Reshape
มุมมอง 379 ชั่วโมงที่ผ่านมา
GDC 2024 - Shader Instrumentation with GPU Reshape
AMD RDNA™ 2 - Radeon™ Developer Tool Suite
มุมมอง 479 ชั่วโมงที่ผ่านมา
AMD RDNA™ 2 - Radeon™ Developer Tool Suite
Webinar - Introduction to Portable GPU Programming
มุมมอง 839 ชั่วโมงที่ผ่านมา
Webinar - Introduction to Portable GPU Programming
Webinar - Profiling and Performance Topics for AMD CDNA GPUs
มุมมอง 419 ชั่วโมงที่ผ่านมา
Webinar - Profiling and Performance Topics for AMD CDNA GPUs
Webinar - PyTorch Performance on CDNA2 and RDNA3
มุมมอง 379 ชั่วโมงที่ผ่านมา
Webinar - PyTorch Performance on CDNA2 and RDNA3
MPI+ Applications on AMD GPUs
มุมมอง 439 ชั่วโมงที่ผ่านมา
MPI Applications on AMD GPUs
Efficient LLM Inference with SGLang, Lianmin Zheng, xAI
มุมมอง 4059 ชั่วโมงที่ผ่านมา
Efficient LLM Inference with SGLang, Lianmin Zheng, xAI
GDC 2024 - GPU Work Graphs: Welcome to the Future of GPU Programming
มุมมอง 1259 ชั่วโมงที่ผ่านมา
GDC 2024 - GPU Work Graphs: Welcome to the Future of GPU Programming
Evolution of Llama: From Herd to Stack, Raghotham Murthy, Meta
มุมมอง 559 ชั่วโมงที่ผ่านมา
Evolution of Llama: From Herd to Stack, Raghotham Murthy, Meta
Efficient Inference on MI300X: Our Journey at Microsoft, Rajat Monga, Microsoft, CVP AI Frameworks
มุมมอง 7849 ชั่วโมงที่ผ่านมา
Efficient Inference on MI300X: Our Journey at Microsoft, Rajat Monga, Microsoft, CVP AI Frameworks
Unlocking Enterprise AI at Scale, Saurabh Baji, Cohere, SVP of Engineering
มุมมอง 709 ชั่วโมงที่ผ่านมา
Unlocking Enterprise AI at Scale, Saurabh Baji, Cohere, SVP of Engineering
The Era of Generative AI in Personal Computing, Adrian Macias,AMD Sr. Director AI Product Management
มุมมอง 1969 ชั่วโมงที่ผ่านมา
The Era of Generative AI in Personal Computing, Adrian Macias,AMD Sr. Director AI Product Management
vLLM: Easy, Fast, and Cheap LLM Serving, Woosuk Kwon, UC Berkeley
มุมมอง 2859 ชั่วโมงที่ผ่านมา
vLLM: Easy, Fast, and Cheap LLM Serving, Woosuk Kwon, UC Berkeley

ความคิดเห็น

  • @joonhojung7765
    @joonhojung7765 7 ชั่วโมงที่ผ่านมา

    라데온좀 잘 만들어라 제발 엔비디아는 쓰기 싫어

  • @TuxTuxedo-oc9kg
    @TuxTuxedo-oc9kg วันที่ผ่านมา

    please instead of wasting ressources on social media, develop rocm support for more hardware. RX 7000+ also! thanks.

  • @legobuildingsrewiew7538
    @legobuildingsrewiew7538 วันที่ผ่านมา

    So thats why they dont care about george hotz

  • @Muffins-Music
    @Muffins-Music วันที่ผ่านมา

    Will there be a video about easy FSR integration? And what about the integration of FSR into chromium? Or will AMD release its browser with FSR?

  • @Valk-Kilmer
    @Valk-Kilmer 2 วันที่ผ่านมา

    Instead of a bunch of random Indians you should be hiring tinygrad who gave you a far better driver solution on current AMD hardware.

  • @AccC-c6d
    @AccC-c6d 3 วันที่ผ่านมา

    Great interview. What wrong with AMD marketing to release this interview so late after the Advancing AI event? AMD lost customer and investor trust after a miserable "Advancing AI" event.

  • @SirMo
    @SirMo 3 วันที่ผ่านมา

    Would be really cool if AMD could extend official support of ROCm to RDNA2 and RDNA3 GPUs. I've tested a number of them and they all work fine. Lack of official support is keeping folks away, as they are under the impression that ROCm doesn't work on those GPUs. I'm pretty sure they all work (I've tested rx6600 and 6700xt, and I also own a 7900xtx which is officially supported). Also a VRAM boosted consumer version of your upcoming GPU would go a long way in attracting folks to ROCm. Like a 32GB version of such a GPU would be a big selling point. At least for us LocalLlama enthusiasts.