Skip to content

Updating QDQ to support Float8E4M3FN#16550

Merged
xadupre merged 39 commits into
microsoft:mainfrom
xadupre:qdq
Aug 8, 2023
Merged

Updating QDQ to support Float8E4M3FN#16550
xadupre merged 39 commits into
microsoft:mainfrom
xadupre:qdq

Conversation

@xadupre
Copy link
Copy Markdown
Member

@xadupre xadupre commented Jun 30, 2023

Description

Naive update quantization tools to support Float8E4M3FN for Gemm.

@xadupre xadupre added the quantization issues related to quantization label Jun 30, 2023
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/test/python/quantization/test_op_gemm.py Fixed
Comment thread onnxruntime/test/python/quantization/test_op_gemm.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/test/python/quantization/test_op_gemm.py Fixed
Copy link
Copy Markdown
Contributor

@justinchuby justinchuby left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just flying by and a few nits :)

Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py
Comment thread onnxruntime/python/tools/quantization/quant_utils.py
Comment thread onnxruntime/python/tools/quantization/quant_utils.py Outdated
Comment thread onnxruntime/python/tools/quantization/quant_utils.py
Comment thread onnxruntime/python/tools/quantization/quantize.py Outdated
Comment thread onnxruntime/test/python/onnxruntime_test_float8.py Outdated
Comment thread onnxruntime/test/python/onnxruntime_test_float8.py Outdated
Comment thread onnxruntime/test/python/quantization/test_op_gemm.py Outdated
Comment thread onnxruntime/test/python/quantization/op_test_utils.py Fixed
Comment thread onnxruntime/test/python/quantization/op_test_utils.py Fixed
Comment thread onnxruntime/python/tools/quantization/quant_utils.py
Copy link
Copy Markdown
Contributor

@github-advanced-security github-advanced-security AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lintrunner found more than 10 potential problems in the proposed changes. Check the Files changed tab for more details.

Comment thread onnxruntime/test/python/quantization/test_op_gemm.py Fixed
Comment thread onnxruntime/python/tools/quantization/calibrate.py Fixed
Comment thread onnxruntime/python/tools/quantization/calibrate.py Fixed
Comment thread onnxruntime/python/tools/quantization/calibrate.py Fixed
Comment thread onnxruntime/python/tools/quantization/calibrate.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/quantize.py Fixed
Comment thread onnxruntime/python/tools/quantization/calibrate.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/python/tools/quantization/operators/conv.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_quantizer.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/python/tools/quantization/onnx_model.py Fixed
Comment thread onnxruntime/test/python/quantization/op_test_utils.py Fixed
@xadupre xadupre marked this pull request as ready for review July 25, 2023 17:14
Comment thread onnxruntime/test/python/quantization/op_test_utils.py Fixed
Comment thread onnxruntime/python/tools/quantization/quant_utils.py
Copy link
Copy Markdown
Member

@yufenglee yufenglee left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

:shipit:

@xadupre xadupre merged commit d0316ee into microsoft:main Aug 8, 2023
jchen351 pushed a commit that referenced this pull request Aug 12, 2023
### Description
Naive update quantization tools to support Float8E4M3FN for Gemm.
kleiti pushed a commit to kleiti/onnxruntime that referenced this pull request Mar 22, 2024
### Description
Naive update quantization tools to support Float8E4M3FN for Gemm.
@xadupre xadupre deleted the qdq branch November 7, 2024 10:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

quantization issues related to quantization

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants