Computer Architectures for training LLM systems – Past Present and Challenges of Future Systems

#IEEEDay #hyderabad #ieeecs #computing #software #lecture #natural #sciences #learning #LLM
Share

Training Large Language Models (LLMs) requires using very large-scale infrastructure, such as dedicated clouds or even a group of clouds. In addition, training such models in a reasonable time requires the use of dedicated Hardware. In my talk, I will emphasize why specialized Hardware for training is needed, present some of the currently proposed solutions, and extend the discussion on the challenges future systems still need to address.


  Date and Time

  Location

  Hosts

  Registration


  • Date: 06 Oct 2024
  • Time: 05:00 PM to 06:00 PM
  • All times are (UTC+05:30) Chennai
  • Add_To_Calendar_icon Add Event to Calendar
If you are not a robot, please complete the ReCAPTCHA to display virtual attendance info.
  • Contact Event Host

  • Vinit Kumar Gunjan, Ph.D.
    Chair IEEE Computer Society and Additional Treasurer 2024
    IEEE Hyderabad Section
    No: 644-645Al-Karim Trade Center,
    Ranigunj,Secunderabad – 500 003.
    Telangana. India.
    Ph:- +91-9441328438

  • Starts 28 September 2024 12:00 AM
  • Ends 06 October 2024 02:00 PM
  • All times are (UTC+05:30) Chennai
  • No Admission Charge

  Speakers

Avi Mendelson of Technion - Israel Institute of Technology

Topic:

Computer Architectures for training LLM systems – Past Present and Challenges of Future Systems

Training Large Language Models (LLMs) requires using very large-scale infrastructure, such as dedicated clouds or even a group of clouds. In addition, training such models in a reasonable time requires the use of dedicated Hardware. In my talk, I will emphasize why specialized Hardware for training is needed, present some of the currently proposed solutions, and extend the discussion on the challenges future systems still need to address.

Biography:

Professor Avi Mendelson is an IEEE Fellow and is currently at the Technion. He has a blend of industrial and academic experiences. Among his industrial experiences, he used to work for National Semiconductors, Intel, and Microsoft R&D Israel. His main research interests are in computer architectures, accelerators for machine learning, and hardware security.

Email:

Address: Technion - Israel Institute of Technology, , Haifa, Israel, 3200003




  Media

Avi Medelson 281.33 KiB