Open
Conversation
unnim-qti
commented
Mar 6, 2026
unnim-qti
commented
- Add Olive support for QNN‑GPU weight sharing through the QNN‑EP.
- Added graph‑surgery pass converting SimplifiedLayerNormalizaton to RMSNorm for QNN‑GPU compatibility.
unnim-qti
changed the title
unnim-qti
changed the title
Author
|
@microsoft-github-policy-service agree company="Qualcomm" |
qti-mattsinc
reviewed
Mar 9, 2026
Comment on lines
+55
to
+61
| "g": { | ||
| "type": "GptqQuantizer", | ||
| "sym": true, | ||
| "group_size": 32, | ||
| "desc_act": false, | ||
| "data_config": "wikitext2_train_joined" | ||
| }, |
There was a problem hiding this comment.
@unnim-qti, should we switch to the GptqModel pass? At some point it would beneficial to do so, since AutoGptq is deprecated in favor of GptqModel, and GptqModel also supports quantization with the CPU instead of requiring CUDA.
Doing so would also have the added benefit of not having to split things up into multiple recipes.
|
|
||
| ```bash | ||
| # Install Olive | ||
| pip install olive-ai==0.9.3 |
There was a problem hiding this comment.
Any reason why we are pinning this to an older release?
|
|
||
| # Install ONNX Runtime QNN | ||
| pip install -r https://raw.githubusercontent.com/microsoft/onnxruntime/refs/heads/main/requirements.txt | ||
| pip install --index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ORT-Nightly/pypi/simple "onnxruntime-qnn==1.22.2" --no-deps |
There was a problem hiding this comment.
Any reason why we are pinning this to an older release?
| To ensure compatibility, please install Olive directly from the source at the required commit: | ||
|
|
||
| ```bash | ||
| pip install git+https://github.com/microsoft/Olive.git@da24463e14ed976503dc5871572b285bc5ddc4b2 |
There was a problem hiding this comment.
Any reason why we are pinning this to a specific commit?
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
2 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.