Reorder ML frameworks and support matrix items on website. (#15719)
* Alphabetize ML frameworks
* The JAX docs are sparse, so I could also see putting PyTorch at the
top of the list
* Change "ONNX" from "(hoped for)" to "(experimental)" and apply the
same "(experimental)" to a few other targets
diff --git a/docs/website/docs/guides/ml-frameworks/index.md b/docs/website/docs/guides/ml-frameworks/index.md
index fc2557c..a77415e 100644
--- a/docs/website/docs/guides/ml-frameworks/index.md
+++ b/docs/website/docs/guides/ml-frameworks/index.md
@@ -27,10 +27,10 @@
See end-to-end examples of how to use each framework with IREE:
-* [:simple-tensorflow: TensorFlow](./tensorflow.md) and
- [:simple-tensorflow: TensorFlow Lite](./tflite.md)
* [:simple-python: JAX](./jax.md)
* [:simple-pytorch: PyTorch](./pytorch.md)
+* [:simple-tensorflow: TensorFlow](./tensorflow.md) and
+ [:simple-tensorflow: TensorFlow Lite](./tflite.md)
Importing from other frameworks is planned - stay tuned!
diff --git a/docs/website/docs/guides/ml-frameworks/pytorch.md b/docs/website/docs/guides/ml-frameworks/pytorch.md
index f675b2a..90f2d86 100644
--- a/docs/website/docs/guides/ml-frameworks/pytorch.md
+++ b/docs/website/docs/guides/ml-frameworks/pytorch.md
@@ -5,7 +5,6 @@
- Python
- PyTorch
icon: simple/pytorch
-status: new
---
# PyTorch + IREE = :octicons-heart-16:
diff --git a/docs/website/docs/index.md b/docs/website/docs/index.md
index f345f77..9865c4b 100644
--- a/docs/website/docs/index.md
+++ b/docs/website/docs/index.md
@@ -25,11 +25,11 @@
IREE supports importing from a variety of ML frameworks:
-- [x] TensorFlow
-- [x] TensorFlow Lite
- [x] JAX
- [x] PyTorch
-- [ ] ONNX (hoped for)
+- [x] TensorFlow
+- [x] TensorFlow Lite
+- [ ] ONNX (experimental)
The IREE compiler tools run on :fontawesome-brands-linux: Linux,
:fontawesome-brands-windows: Windows, and :fontawesome-brands-apple: macOS
@@ -37,11 +37,11 @@
- [x] Linux
- [x] Windows
-- [x] Android
- [x] macOS
+- [x] Android
- [x] iOS
- [x] Bare metal
-- [ ] WebAssembly (planned)
+- [ ] WebAssembly (experimental)
and architectures:
@@ -54,7 +54,9 @@
- [x] Vulkan
- [x] CUDA
- [x] Metal (for Apple silicon devices)
-- [ ] WebGPU (planned)
+- [ ] ROCm (experimental)
+- [ ] AMD AIE (experimental)
+- [ ] WebGPU (experimental)
## Project architecture
@@ -96,10 +98,10 @@
IREE supports importing models from a growing list of ML frameworks and model
formats:
-* [TensorFlow](./guides/ml-frameworks/tensorflow.md) and
- [TensorFlow Lite](./guides/ml-frameworks/tflite.md)
* [JAX](./guides/ml-frameworks/jax.md)
* [PyTorch](./guides/ml-frameworks/pytorch.md)
+* [TensorFlow](./guides/ml-frameworks/tensorflow.md) and
+ [TensorFlow Lite](./guides/ml-frameworks/tflite.md)
### Selecting deployment configurations
diff --git a/docs/website/mkdocs.yml b/docs/website/mkdocs.yml
index 988fd58..f90dbd4 100644
--- a/docs/website/mkdocs.yml
+++ b/docs/website/mkdocs.yml
@@ -127,10 +127,10 @@
- "guides/index.md"
- "ML frameworks":
- "guides/ml-frameworks/index.md"
- - TensorFlow: "guides/ml-frameworks/tensorflow.md"
- - TensorFlow Lite: "guides/ml-frameworks/tflite.md"
- JAX: "guides/ml-frameworks/jax.md"
- PyTorch: "guides/ml-frameworks/pytorch.md"
+ - TensorFlow: "guides/ml-frameworks/tensorflow.md"
+ - TensorFlow Lite: "guides/ml-frameworks/tflite.md"
- "Deployment configurations":
- "guides/deployment-configurations/index.md"
- CPU: "guides/deployment-configurations/cpu.md"
