TT-Buda™

Great for production customers who want to get models up and running with ease. They want flexibility, but don’t have time to program new operations or contact support every time something changes.
TT-Buda™

Looking for TT-Metalium™, our bottom up SDK for direct access to Tenstorrent hardware? TT-Metalium™ Doc Site

TT-Buda™ Architecture

TT-Buda™ is a high-level SDK that intakes AI frameworks and employs a top-down approach, generating a program file to run an AI model on Tenstorrent hardware. Its compiler front-end runs synthesis checks and verifies that all functions of the AI model are supported before synthesizing a human-readable netlist of operations.

TT-Buda™ GitHub
Features:
TT-Buda™ is Tenstorrent’s framework which allows standard AI software to run on our hardware.
TT-Buda™ is Tenstorrent’s framework which allows standard AI software to run on our hardware.
TT-Buda™ enables you to run common models like Llama, U-Net, and Yolo or something built from the ground up.
TT-Buda™ enables you to run common models like Llama, U-Net, and Yolo or something built from the ground up.
We provide a variety of development tools that include performance tuning, place & route analysis, debug, graph review, and more.
We provide a variety of development tools that include performance tuning, place & route analysis, debug, graph review, and more.

Looking for additional information?