[native] Add an ExecuTorch Native docs page

docs/source/advanced-topics-section.md

@@ -102,6 +102,18 @@ Key topics:
 - PTD file format specification
 - Custom file format handling
 
+## ExecuTorch Native
+
+Experimental: export a model to a single `.ptn` file and run it on one of
+several engines.
+
+**→ {doc}`native-overview` — ExecuTorch Native**
+
+Key topics:
+
+- Export with `to_native` and the `.ptn` file
+- Runtime engines
+
 ## Next Steps
 
 After exploring advanced topics:
@@ -122,4 +134,5 @@ backend-delegate-advanced
 runtime-integration-advanced
 compiler-ir-advanced
 file-formats-advanced
+native-overview
 ```

docs/source/native-overview.md

@@ -0,0 +1,72 @@
+(native-overview)=
+
+# ExecuTorch Native
+
+::::{note}
+ExecuTorch Native is experimental. The Python API, the `.ptn` format, and
+operator coverage may change.
+::::
+
+ExecuTorch Native lowers a PyTorch model to a single `.ptn` file and runs it on
+one of several engines. In a `.pte`, delegates lower the graph ahead of time for
+specific backends. A `.ptn` keeps the whole graph without backend-specific
+information, and each engine lowers it when compiling a method.
+
+```text
+.pte:  export -> [quantize] -> to_edge -> to_backend -> to_executorch -> .pte (+ .ptd)
+.ptn:  export -> [quantize] -> to_native -> .ptn
+```
+
+<img src="_static/img/native-pipeline.png" alt="ExecuTorch Native pipeline: a PyTorch model goes through torch.export and to_native into a .ptn file, which the Native runtime hands to an engine on the device" style="width:600px;"/>
+
+## Export
+
+```python
+import torch
+from executorch.exir.native import to_native
+
+ep = torch.export.export(model, example_inputs)
+to_native(ep).save("model.ptn")
+
+# Several methods in one file.
+to_native({"forward": ep_forward, "prefill": ep_prefill}).save("model.ptn")
+```
+
+The partitioner accepts core ATen ops plus `linear`, `matmul`, `addmm`,
+`scaled_dot_product_attention`, `rms_norm`, `native::rope`, and TorchAO affine
+quantize/dequantize ops. TorchAO int4 group-wise weights of `linear` and
+`embedding`, and GGUF k-quant weights from `executorch.extension.llm.export.gguf`,
+are stored packed with their scheme in tensor metadata. Each method must lower
+wholly to one delegate; `to_native` raises otherwise.
+
+A `.ptn` is an uncompressed zip with fixed entry names:
+
+| Entry | Contents |
+| --- | --- |
+| `program.ptg` | Methods as graphs; FlatBuffer defined by [`native_graph.fbs`](https://github.com/pytorch/executorch/blob/main/backends/native/serialization/native_graph.fbs). |
+| `program.safetensors` | Constants. Byte-identical immutable tensors are stored once. |
+| `aliases.json` | Deduplicated key to owner key; present only when needed. |
+
+## Runtime
+
+The C++ runtime reads a `.ptn` into an in-memory graph and hands each method to
+an engine through the interfaces in
+[`Engine.h`](https://github.com/pytorch/executorch/blob/main/backends/native/runtime/engine/Engine.h).
+
+- `EngineHost`: process-wide device resources.
+- `EngineContext`: state for one loaded program, including mutable buffers.
+- `EngineExecutable`: one compiled method (`set_input`, `execute`, `get_output`).
+
+An engine rejects a method whose semantics it cannot fully honor.
+
+| Engine | Notes |
+| --- | --- |
+| Vulkan | Builds on the ET-VK `ComputeGraph` and shaders. |
+| ggml | CPU, CUDA, HIP, and Metal variants. |
+
+The runtime currently builds only with Meta's internal Buck setup; there is no
+open-source build yet.
+
+The source is in
+[`exir/native/`](https://github.com/pytorch/executorch/tree/main/exir/native) and
+[`backends/native/`](https://github.com/pytorch/executorch/tree/main/backends/native).