Bump torchao + add unit tests for torchao kernels #9396
Merged
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9396
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Cancelled Job, 2 PendingAs of commit ad95321 with merge base 7a2a300 ( NEW FAILURE - The following job has failed:
CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
metascroy
force-pushed
the
torchao-up
branch
2 times, most recently
from
3f4b66d to
531d8ca
Compare
metascroy
changed the title
metascroy
requested review from
GregoryComer,
lucylq and
jackzhxng
as code owners
jackzhxng
approved these changes
Mar 20, 2025
| -d fp32 | ||
|
|
||
| # Test run | ||
| ./cmake-out/examples/models/llama/llama_main --model_path=$MODEL_OUT --tokenizer_path=$TOKENIZER --prompt="Once upon a time," |
There was a problem hiding this comment.
Should we do a simple non-brittle sanity check? e.g. output length > 0 or something
There was a problem hiding this comment.
I think the main concern is whether it runs. If it runs, it will produce output.
examples/models/llama/README.md
Outdated
| @@ -380,6 +380,79 @@ Please refer to [this tutorial](https://pytorch.org/executorch/main/llm/llama-de | |||
| ### Android | |||
| Please refer to [this tutorial](https://pytorch.org/executorch/main/llm/llama-demo-android.html) to for full instructions on building the Android LLAMA Demo App. | |||
|
|
|||
| ## Running with low-bit kernels | |||
|
|
|||
| We now give instructions for quantizating and running your model with low-bit kernels. These are still experimental, and require you do development on an Arm-based Mac. Also note that low-bit quantization often requires QAT (quantization-aware training) to give good quality results. | |||
There was a problem hiding this comment.
Might be worth saying that these don't work with dynamic shapes yet
jackzhxng
added
the
release notes: build
oscarandersson8218
pushed a commit
to oscarandersson8218/executorch
that referenced
this pull request
Mar 21, 2025
### Summary This PR bumps the torchao pin and adds unit tests and documentation for the lowbit torchao kernels. ### Test plan New CI test
DannyYuyang-quic
pushed a commit
to CodeLinaro/executorch
that referenced
this pull request
Apr 2, 2025
### Summary This PR bumps the torchao pin and adds unit tests and documentation for the lowbit torchao kernels. ### Test plan New CI test
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary
This PR bumps the torchao pin and adds unit tests and documentation for the lowbit torchao kernels.
Test plan
New CI test