add extra_options use_channel_wised_quantization to builder.py #1362
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
|
@microsoft-github-policy-service agree |
…ize the model with block size = K
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Outdated suggestions cannot be applied.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.
Add extra options to builder.py
enable quantize the model with block size = K
this PR want to work with intel/onnxruntime#631 to enable channel wised quantization capability of onnxruntime genai to generate symmetric and block_size = -1 quantized model.
with this format model, Intel NPU is able to runs x20+ speed up compared to original block size 16/32/64/128/256 models.
command:
python -m onnxruntime_genai.models.builder -o E:\download\onnx\Phi-3-mini-4k-instruct-onnx-channelwise-modified -p int4 -e cpu -i E:\download\huggingface\Phi-3-mini-4k-instruct --extra_options use_channel_wised_quantization=1 use_qdq=1