You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 6e8b206
Browse filesBrowse the repository at this point in the historyBrowse files
Update documentation with new ecosystem integrations, demos, and resource links (pytorch#16371)
docs/source/success-stories.md
1. Added Arm ML Embedded Evaluation Kit to Ecosystem Integrations
(Cortex-M, Ethos-U NPUs)
2. Added Whisper to Featured Demos (CUDA and Metal backends)
3. Added Audio Generation demo (Stable Audio Open Small on Arm CPUs with
KleidiAI)
4. Added YouTube video link to Audio Generation demo
5. Added Alif Semiconductor Ensemble to Ecosystem Integrations (E4/E6/E8
MCUs with Ethos-U85)
6. Added blog link to Ultralytics entry
7. Added Digica AI SDK to Ecosystem Integrations (ExecuTorch-powered SDK
for iOS/Android/edge)
README.md (top-level)
1. Updated Whisper link from external repo to local
examples/models/whisper/README.md
2. Added Unsloth to Resources line for fine-tuned LLM deployment
3. Added Desktop Guide link for CUDA/Metal GPU inference
4. Added Zephyr Guide link for Zephyr RTOS integration
examples/models/whisper/README.md
1. Added Mobile Demo section with link to Android WhisperApp
website/index.html
1. Updated Whisper link to in-tree whisper README
2. Added Reality Labs blog link to Production Deployments
3. Added LiquidAI blog link to Ecosystem Integration
4. Added Software Mansion link to Ecosystem Integration
examples/qualcomm/oss_scripts/llama/README.md
1. Added YouTube video tutorial "Build Along: Run LLMs Locally on
Qualcomm Hardware Using ExecuTorch"
docs/source/backends-cadence.md
1. Added Cadence blog link about running optimized PyTorch models on
Cadence DSPs
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
See [Backend Documentation](https://docs.pytorch.org/executorch/main/backends-overview.html) for detailed hardware requirements and optimization guides.
195
+
See [Backend Documentation](https://docs.pytorch.org/executorch/main/backends-overview.html) for detailed hardware requirements and optimization guides. For desktop/laptop GPU inference with CUDA and Metal, see the [Desktop Guide](desktop/README.md). For Zephyr RTOS integration, see the [Zephyr Guide](zephyr/README.md).
196
196
197
197
## Production Deployments
198
198
@@ -204,9 +204,9 @@ ExecuTorch powers on-device AI at scale across Meta's family of apps, VR/AR devi
Copy file name to clipboardExpand all lines: docs/source/backends-cadence.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,6 +10,8 @@ In this tutorial we will walk you through the process of getting setup to build
10
10
11
11
In addition to the chip, the HiFi4 Neural Network Library ([nnlib](https://github.com/foss-xtensa/nnlib-hifi4)) offers an optimized set of library functions commonly used in NN processing that we utilize in this example to demonstrate how common operations can be accelerated.
12
12
13
+
For an overview of the Cadence ExecuTorch integration with performance benchmarks, see the blog post: [Running Optimized PyTorch Models on Cadence DSPs with ExecuTorch](https://community.cadence.com/cadence_blogs_8/b/ip/posts/running-optimized-pytorch-models-on-cadence-dsps-with-executorch).
14
+
13
15
On top of being able to run on the Xtensa HiFi4 DSP, another goal of this tutorial is to demonstrate how portable ExecuTorch is and its ability to run on a low-power embedded device such as the Xtensa HiFi4 DSP. This workflow does not require any delegates, it uses custom operators and compiler passes to enhance the model and make it more suitable to running on Xtensa HiFi4 DSPs. A custom [quantizer](https://pytorch.org/tutorials/prototype/quantization_in_pytorch_2_0_export_tutorial.html) is used to represent activations and weights as `uint8` instead of `float`, and call appropriate operators. Finally, custom kernels optimized with Xtensa intrinsics provide runtime acceleration.
@@ -126,8 +152,12 @@ Deploy on-device inference for Ultralytics YOLO models using ExecuTorch.
126
152
127
153
-**Voxtral** - Deploy audio-text-input LLM on CPU (via XNNPACK) and on CUDA. [Try →](https://github.com/pytorch/executorch/blob/main/examples/models/voxtral/README.md)
128
154
155
+
-**Whisper** - Deploy OpenAI's Whisper speech recognition model on CUDA and Metal backends. [Try →](https://github.com/pytorch/executorch/blob/main/examples/models/whisper/README.md)<!-- @lint-ignore -->
156
+
129
157
-**LoRA adapter** - Export two LoRA adapters that share a single foundation weight file, saving memory and disk space. [Try →](https://github.com/meta-pytorch/executorch-examples/tree/main/program-data-separation/cpp/lora_example)
130
158
131
159
-**OpenVINO from Intel** - Deploy [Yolo12](https://github.com/pytorch/executorch/tree/main/examples/models/yolo12), [Llama](https://github.com/pytorch/executorch/tree/main/examples/openvino/llama), and [Stable Diffusion](https://github.com/pytorch/executorch/tree/main/examples/openvino/stable_diffusion) on [OpenVINO from Intel](https://www.intel.com/content/www/us/en/developer/articles/community/optimizing-executorch-on-ai-pcs.html).
132
160
161
+
-**Audio Generation** - Generate audio from text prompts using Stable Audio Open Small on Arm CPUs with XNNPACK and KleidiAI. [Try →](https://github.com/Arm-Examples/ML-examples/tree/main/kleidiai-examples/audiogen-et) • [Video →](https://www.youtube.com/watch?v=q2P0ESVxhAY)<!-- @lint-ignore -->
162
+
133
163
*Want to showcase your demo? [Submit here →](https://github.com/pytorch/executorch/issues)*
For an Android demo app, see the [Whisper Android App](https://github.com/meta-pytorch/executorch-examples/tree/main/whisper/android/WhisperApp) in the executorch-examples repository. <!-- @lint-ignore -->
Copy file name to clipboardExpand all lines: examples/qualcomm/oss_scripts/llama/README.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,9 @@
1
1
# Summary
2
2
3
3
## Overview
4
+
5
+
**Video Tutorial:**[Build Along: Run LLMs Locally on Qualcomm Hardware Using ExecuTorch](https://www.youtube.com/watch?v=41PKDlGM3oU)
6
+
4
7
This file provides you the instructions to run LLM Decoder model with different parameters via Qualcomm HTP backend. We currently support the following models:
5
8
<!-- numbered list will be automatically generated -->
<li><strongclass="highlight"><ahref="https://engineering.fb.com/2025/07/28/android/executorch-on-device-ml-meta-family-of-apps/" style="color: var(--primary); text-decoration: none;">Meta Family of Apps</a>:</strong> Production deployment across Instagram, Facebook, and WhatsApp serving billions of users</li>
921
-
<li><strongclass="highlight">Meta Reality Labs:</strong> Powers Quest 3 VR and Ray-Ban Meta Smart Glasses AI experiences</li>
921
+
<li><strongclass="highlight"><ahref="https://ai.meta.com/blog/executorch-reality-labs-on-device-ai/" style="color: var(--primary); text-decoration: none;">Meta Reality Labs</a>:</strong> Powers Quest 3 VR and Ray-Ban Meta Smart Glasses AI experiences</li>
<li><strongclass="highlight"><ahref="https://github.com/huggingface/optimum-executorch" style="color: var(--primary); text-decoration: none;">Hugging Face</a>:</strong> Optimum-ExecuTorch for direct transformer model deployment</li>
929
-
<li><strongclass="highlight">LiquidAI:</strong> Next-generation Liquid Foundation Models optimized for edge deployment</li>
930
-
<li><strongclass="highlight">Software Mansion:</strong> React Native ExecuTorch bringing edge AI to mobile apps</li>
929
+
<li><strongclass="highlight"><ahref="https://www.liquid.ai/blog/how-liquid-ai-uses-executorch-to-power-efficient-flexible-on-device-intelligence" style="color: var(--primary); text-decoration: none;">LiquidAI</a>:</strong> Next-generation Liquid Foundation Models optimized for edge deployment</li>
930
+
<li><strongclass="highlight"><ahref="https://docs.swmansion.com/react-native-executorch/" style="color: var(--primary); text-decoration: none;">Software Mansion</a>:</strong> React Native ExecuTorch bringing edge AI to mobile apps</li>
0 commit comments