Extend supported types by QLinearMatMul (float16, float 8 types) #5473
Conversation
This file contains 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
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
xadupre
changed the title
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: xadupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
justinchuby
reviewed
Aug 30, 2023
justinchuby
reviewed
Aug 30, 2023
gramalingam
reviewed
Aug 31, 2023
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
gramalingam
approved these changes
Sep 1, 2023
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
|
Tks @xadupre Does it mean int4 is not yet supported ? |
|
Int4 is not defined yet in onnx. That would be the first step before adding it to the list of supported types. Maybe it would be worth discussing it during one of the sig meeting. |
gramalingam
requested changes
Sep 19, 2023
|
Moved to 1.16 |
|
That s unfortunate. What about reducing the scope and at least add uint8/int8 (no float8)? |
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
xadupre
changed the title
Codecov ReportAttention:
Additional details and impacted files@@ Coverage Diff @@
## main #5473 +/- ##
==========================================
- Coverage 56.06% 56.04% -0.02%
==========================================
Files 501 501
Lines 29366 29409 +43
Branches 4404 4413 +9
==========================================
+ Hits 16463 16482 +19
- Misses 12091 12115 +24
Partials 812 812 ☔ View full report in Codecov by Sentry. |
gramalingam
reviewed
Nov 1, 2023
Signed-off-by: Xavier Dupre <xadupre@microsoft.com>
justinchuby
approved these changes
Nov 7, 2023
gramalingam
approved these changes
Nov 14, 2023
xadupre
added a commit
to microsoft/onnxruntime
that referenced
this pull request
Jan 12, 2024
…hts (#18043) ### Description Whenever a node QuantizeLinear or DequantizeLinear, the type of the weights before being quantize must be known to create the scale with the expected type. Another option would be to add many operator CastLike but that would push the burden to onnxruntime optimizer. The PR tries to avoid changing the signature. To do so, it modified the scale computation to use a numpy array to store the result and not a python float. The numpy array must be of the same type than the weights to quantize. The PR adds many `assert` to check the type of the scale is not a python type or a float64. This was added to make sure all the code follows the same logic. These lines were kept for the first review. DequantizeLinear, QuantizeLinear cannot be tested with onnx==1.15. PR onnx/onnx#5709 is missing to fix shape inference. PR onnx/onnx#5473) is missing to support QLinearMatMul with float 16. That explains why some tests are disabled with float 16. ### Motivation and Context The current quantization tool assumes every weight is float 32. For large models such as LLAMA, it is usually float 16. The quantization needs to quantize such weights.
mszhanyi
pushed a commit
to microsoft/onnxruntime
that referenced
this pull request
Jan 15, 2024
…hts (#18043) ### Description Whenever a node QuantizeLinear or DequantizeLinear, the type of the weights before being quantize must be known to create the scale with the expected type. Another option would be to add many operator CastLike but that would push the burden to onnxruntime optimizer. The PR tries to avoid changing the signature. To do so, it modified the scale computation to use a numpy array to store the result and not a python float. The numpy array must be of the same type than the weights to quantize. The PR adds many `assert` to check the type of the scale is not a python type or a float64. This was added to make sure all the code follows the same logic. These lines were kept for the first review. DequantizeLinear, QuantizeLinear cannot be tested with onnx==1.15. PR onnx/onnx#5709 is missing to fix shape inference. PR onnx/onnx#5473) is missing to support QLinearMatMul with float 16. That explains why some tests are disabled with float 16. ### Motivation and Context The current quantization tool assumes every weight is float 32. For large models such as LLAMA, it is usually float 16. The quantization needs to quantize such weights.
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.
Description
QLinearMatMul is used on quantized types. This PR extends the list of supported quantized types to float 8 types and the list of supported inputs types to float16, bfloat16.