TT-Forge FE is a graph compiler designed to optimize and transform computational graphs for deep learning models, enhancing their performance and efficiency.
- Getting Started / How to Run a Model
- Build - Use these instructions if you plan to do development work.
TT-Forge-FE is a front end component within the broader tt-forge ecosystem, which is designed to compile and execute machine learning models on Tenstorrent hardware platforms like Wormhole and Blackhole. tt-forge-fe can ingest models from various machine learning frameworks including PyTorch, ONNX, and TensorFlow through the TVM Intermediate Representation (IR).
-
- A TVM based graph compiler designed to optimize and transform computational graphs for deep learning models. Supports ingestion of PyTorch, ONNX, TensorFlow, PaddlePaddle and similar ML frameworks via TVM (TT-TVM).
- See docs pages for an overview and getting started guide.
-
- A MLIR-native, open-source, PyTorch 2.X and torch-mlir based front-end. It provides stableHLO (SHLO) graphs to TT-MLIR. Supports ingestion of PyTorch models via PT2.X compile and ONNX models via torch-mlir (ONNX->SHLO)
- See docs pages for an overview and getting started guide.
-
- Leverages a PJRT interface to integrate JAX (and in the future other frameworks), TT-MLIR and Tenstorrent hardware. Supports ingestion of JAX models via jit compile, providing StableHLO (SHLO) graph to TT-MLIR compiler
- See Getting Started for an overview and getting started guide.
You can run a demo using the TT-Forge-FE Getting Started page.
This repo is a part of Tenstorrent’s bounty program. If you are interested in helping to improve tt-forge, please make sure to read the Tenstorrent Bounty Program Terms and Conditions before heading to the issues tab. Look for the issues that are tagged with both “bounty” and difficulty level!
