embedded: add ExecuTorch Vulkan learning path for Android - #3625
Merged
Conversation
Add a new embedded learning path showing how to export Llama 3.2 1B Instruct with ExecuTorch, build the Android Vulkan runtime, and deploy, run, validate, and measure it on a Vivo X300 Pro. Signed-off-by: Ash Naik <ash.naik@arm.com>
ashnaik-arm
marked this pull request as ready for review
August 12, 2026 14:11
BmanClark
reviewed
Aug 13, 2026
| - Build, deploy, validate, and troubleshoot the Android `llama_main` runner on a Vivo X300 Pro. | ||
|
|
||
| prerequisites: | ||
| - A Linux host with enough disk space for the ExecuTorch source tree, Android SDK and NDK, Vulkan SDK, and the Llama checkpoint. |
Contributor
There was a problem hiding this comment.
it probably doesn't need to be Linux? Can cross-compile from Mac or Windows (maybe easier in WSL admittedly)
| - A Vivo X300 Pro or a similar Android phone with USB debugging enabled. | ||
| - Access to the gated Hugging Face repository `meta-llama/Llama-3.2-1B-Instruct`. | ||
| - Working familiarity with the shell, Python virtual environments, and Android ADB workflows. | ||
|
|
Contributor
There was a problem hiding this comment.
added prerequisite of Python 3.12 (either that or install it in one of the steps)
BmanClark
reviewed
Aug 13, 2026
|
|
||
| minutes_to_complete: 120 | ||
|
|
||
| who_is_this_for: This Learning Path is for developers who want to export a Llama 3.2 model with ExecuTorch and run it on an Android phone through the Vulkan backend. |
Contributor
There was a problem hiding this comment.
good to make this line more general about model
BmanClark
reviewed
Aug 13, 2026
| Upon completion of this Learning Path, you will be able to: | ||
|
|
||
| - Prepare the Android SDK, NDK, ADB, and host Vulkan toolchain required for cross-compiling ExecuTorch. | ||
| - Fix the PyTorch version mismatch that can break ExecuTorch 1.4 builds on the host. |
Contributor
There was a problem hiding this comment.
Is this a big enough / common enough problem that we want to feature it on the front page? (if it is a common issue, then it could belong here)
BmanClark
reviewed
Aug 13, 2026
|
|
||
| - Prepare the Android SDK, NDK, ADB, and host Vulkan toolchain required for cross-compiling ExecuTorch. | ||
| - Fix the PyTorch version mismatch that can break ExecuTorch 1.4 builds on the host. | ||
| - Export Llama 3.2 1B Instruct to a Vulkan-ready `.pte` using the same `8da4w` and KV-cache settings as the measured run. |
Contributor
There was a problem hiding this comment.
Again, as a front page, might want the more general "Export an LLM to a vulkan-ready..."
BmanClark
reviewed
Aug 13, 2026
| - Android Studio or an equivalent Android SDK and NDK installation path. | ||
| - A phone connected over USB with developer mode and USB debugging enabled. | ||
| - Hugging Face access to download `meta-llama/Llama-3.2-1B-Instruct`. | ||
| - Sufficient storage for a multi-gigabyte checkpoint and exported `.pte`. |
Contributor
There was a problem hiding this comment.
Could this be more specific? ie "At least xGB of storage free"
BmanClark
reviewed
Aug 13, 2026
|
|
||
| - A Linux machine that can build native and Android targets. | ||
| - Android Studio or an equivalent Android SDK and NDK installation path. | ||
| - A phone connected over USB with developer mode and USB debugging enabled. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a new embedded learning path showing how to export "Llama 3.2 1B Instruct" with ExecuTorch, build the Android Vulkan runtime, and deploy, run, validate, and measure it on a Vivo X300 Pro.