llama 3.1 8b QNN recipie update#516
Open
rM-planet wants to merge 1 commit into
Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the Llama 3.1 8B QAIRT recipe to align with newer QAIRT tooling and add an SC8380XP (X Elite) run path, including updated installation instructions and updated encapsulation settings.
Changes:
- Bump validated
qairt-devversion and adjust install instructions to use a pinned Olive commit. - Add X Elite run command and introduce SC8380XP encapsulation override settings.
- Switch AIMET HTP quantsim config selection to local JSON files and add
htp_quantsim_config_v73.json.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| meta-llama-Llama-3.1-8B-Instruct/QAIRT/README.md | Updates validated versions and installation/run instructions (adds X Elite command). |
| meta-llama-Llama-3.1-8B-Instruct/QAIRT/llama3_1_instruct_script.py | Changes HTP quantsim config pathing to local config filenames. |
| meta-llama-Llama-3.1-8B-Instruct/QAIRT/htp_sc8380xp.json | Adds encapsulation engine/backend override settings for SC8380XP. |
| meta-llama-Llama-3.1-8B-Instruct/QAIRT/htp_quantsim_config_v73.json | Adds a bundled AIMET quantsim config for HTP v73 targets. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
|
||
| # Select quantsim config based on target | ||
| htp_config_file_adascale = f'{sys.prefix}/lib/python3.10/site-packages/aimet_common/quantsim_config/htp_quantsim_config_{nsp_target_adascale.dsp_arch}.json' | ||
| htp_config_file_adascale = f'htp_quantsim_config_{nsp_target_adascale.dsp_arch}.json' |
|
|
||
| # Select quantsim config based on target | ||
| htp_config_file = f'{sys.prefix}/lib/python3.10/site-packages/aimet_common/quantsim_config/htp_quantsim_config_{nsp_target.dsp_arch}.json' | ||
| htp_config_file = f'htp_quantsim_config_{nsp_target.dsp_arch}.json' |
rM-planet
force-pushed
the
mlperf_2_llama
branch
2 times, most recently
from
08b4284 to
5b8f1ca
Compare
Contributor
Author
|
@jambayk Please review and merge the recipie update for llama 3.1 8b |
qti-kromero
reviewed
Jun 24, 2026
|
|
||
| # Select quantsim config based on target | ||
| htp_config_file_adascale = f'{sys.prefix}/lib/python3.10/site-packages/aimet_common/quantsim_config/htp_quantsim_config_{nsp_target_adascale.dsp_arch}.json' | ||
| htp_config_file_adascale = f"htp_quantsim_config_v73.json" |
Contributor
There was a problem hiding this comment.
should this always be the v73 quantsim config?
Contributor
Author
There was a problem hiding this comment.
Well, v73 and v81 configs are exactly the same. So doesn't matter!
| pip install --no-build-isolation git+https://github.com/microsoft/Olive.git@f7efd41ab24a2eb07be7edc6d84d0f6304b46598 | ||
| pip list | grep qairt-dev # Ensure the proper qairt-dev version was installed | ||
| pip install qairt-dev[onnx]==0.5.0 # Install the proper qairt-dev version, if not installed | ||
| pip install qairt-dev==0.8.1 # Install the proper qairt-dev version, if not installed |
Contributor
There was a problem hiding this comment.
this is good without the [onnx]?
Contributor
Author
There was a problem hiding this comment.
Added the [onnx] dependency
rM-planet
force-pushed
the
mlperf_2_llama
branch
from
5b8f1ca to
bca3ea8
Compare
Contributor
Author
|
@jambayk Requesting you to merge the recipie! |
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
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.
No description provided.