Skip to content

Commit f0112a2

Browse files
cmodi-metafacebook-github-bot
authored andcommitted
Add MTK NeuroPilot Portal link for SDK in mediatek_README.md (#5872)
Summary: Pull Request resolved: #5872 Reviewed By: cccclai Differential Revision: D63883076 Pulled By: cmodi-meta fbshipit-source-id: 858b222bc622b3076c765e9ea1166ff032675e03
1 parent f3de2bb commit f0112a2

File tree

1 file changed

+5
-7
lines changed

1 file changed

+5
-7
lines changed

examples/demo-apps/android/LlamaDemo/docs/delegates/mediatek_README.md

Lines changed: 5 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -12,7 +12,11 @@ Phone verified: MediaTek Dimensity 9300 (D9300) chip.
1212
* Download and link the Buck2 build, Android NDK, and MediaTek ExecuTorch Libraries from the MediaTek Backend Readme ([link](https://github.com/pytorch/executorch/tree/main/backends/mediatek/scripts#prerequisites)).
1313
* MediaTek Dimensity 9300 (D9300) chip device
1414
* Desired Llama 3 model weights. You can download them on HuggingFace [Example](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)).
15-
* `libneuronusdk_adapter.mtk.so`, `libneuron_buffer_allocator.so`, and `.whl` files (will be available soon by MediaTek)
15+
* Download NeuroPilot Express SDK from the [MediaTek NeuroPilot Portal](https://neuropilot.mediatek.com/resources/public/npexpress/en/docs/npexpress) (coming soon):
16+
- `libneuronusdk_adapter.mtk.so`: This universal SDK contains the implementation required for executing target-dependent code on the MediaTek chip.
17+
- `libneuron_buffer_allocator.so`: This utility library is designed for allocating DMA buffers necessary for model inference.
18+
- `mtk_converter-8.8.0.dev20240723+public.d1467db9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl`: This library preprocess the model into a MediaTek representation.
19+
- `mtk_neuron-8.2.2-py3-none-linux_x86_64.whl`: This library converts the model to binaries.
1620

1721
## Setup ExecuTorch
1822
In this section, we will need to set up the ExecuTorch repo first with Conda environment management. Make sure you have Conda available in your system (or follow the instructions to install it [here](https://anaconda.org/anaconda/conda)). The commands below are running on Linux (CentOS).
@@ -42,11 +46,6 @@ Install dependencies
4246
zstd -cdq "<downloaded_buck2_file>.zst" > "<path_to_store_buck2>/buck2" && chmod +x "<path_to_store_buck2>/buck2"
4347
```
4448

45-
### MediaTek ExecuTorch Libraries
46-
The following libraries will be available soon by MediaTek:
47-
libneuronusdk_adapter.mtk.so: This universal SDK contains the implementation required for executing target-dependent code on the MediaTek chip.
48-
libneuron_buffer_allocator.so: This utility library is designed for allocating DMA buffers necessary for model inference.
49-
5049
### Set Environment Variables
5150
```
5251
export BUCK2=path_to_buck/buck2 # Download BUCK2 and create BUCK2 executable
@@ -75,7 +74,6 @@ MTK currently supports Llama 3 exporting.
7574
// Ensure that you are inside executorch/examples/mediatek directory
7675
pip3 install -r requirements.txt
7776
78-
// The following .whl file will be available soon
7977
pip3 install mtk_neuron-8.2.2-py3-none-linux_x86_64.whl
8078
pip3 install mtk_converter-8.8.0.dev20240723+public.d1467db9-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
8179
```

0 commit comments

Comments
 (0)