# TT-XLA Documentation

TT-XLA is a PJRT-based backend integration that enables JAX and PyTorch/XLA
to run on Tenstorrent AI hardware.

```{toctree}
:caption: Getting Started
:maxdepth: 2

getting_started
getting_started_debugging
```

```{toctree}
:caption: Performance
:maxdepth: 2

performance
mixed_precision
```

```{toctree}
:caption: Testing
:maxdepth: 2

test_infra
model_auto_discovery_tests
```

```{toctree}
:caption: Compiler Internals
:maxdepth: 2

fusing_and_composite_ops
```

```{toctree}
:caption: Code Generation
:maxdepth: 2

getting_started_codegen
emitpy_tutorial
troubleshooting_codegen
```

```{toctree}
:caption: Build & Tools
:maxdepth: 2

torch_xla_build
tools
tt_explorer
bisect_improvements
```