Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[DML] Add int4 QDQ #21592

Merged
merged 9 commits into from
Aug 21, 2024
Merged

[DML] Add int4 QDQ #21592

merged 9 commits into from
Aug 21, 2024

Conversation

PatriceVignola
Copy link
Contributor

No description provided.

github-advanced-security[bot]
github-advanced-security bot found potential problems Aug 2, 2024
View reviewed changes
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
@@ -437,6 +437,12 @@
static const int sc_sinceVer_ReduceMin = 20;
}

namespace OnnxOperatorSet21
{
static const int sc_sinceVer_QuantizeLinear = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_QuantizeLinear' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_QuantizeLinear' can be computed at compile-time. Consider using constexpr (con.5).
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
namespace OnnxOperatorSet21
{
static const int sc_sinceVer_QuantizeLinear = 21;
static const int sc_sinceVer_DequantizeLinear = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_DequantizeLinear' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_DequantizeLinear' can be computed at compile-time. Consider using constexpr (con.5).
@PatriceVignola
Copy link
Contributor Author

/azp run Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

fdwr
fdwr previously approved these changes Aug 2, 2024
View reviewed changes
onnxruntime/test/providers/cpu/tensor/quantize_linear_test.cc Show resolved Hide resolved
onnxruntime/test/providers/cpu/tensor/quantize_linear_test.cc Show resolved Hide resolved
onnxruntime/core/providers/dml/OperatorAuthorHelper/MLOperatorAuthorHelper.h Outdated Show resolved Hide resolved
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/OperatorRegistration.cpp Show resolved Hide resolved
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorElementWise.cpp Outdated Show resolved Hide resolved
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorElementWise.cpp Outdated Show resolved Hide resolved
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorElementWise.cpp Outdated Show resolved Hide resolved
onnxruntime/core/providers/dml/DmlExecutionProvider/src/Operators/DmlOperatorElementWise.cpp Outdated Show resolved Hide resolved
@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU Doc Gen CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola PatriceVignola requested a review from fdwr August 7, 2024 06:25
@PatriceVignola
Copy link
Contributor Author

/azp run Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU DML CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU DML CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

github-advanced-security[bot]
github-advanced-security bot found potential problems Aug 9, 2024
View reviewed changes
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
{
static const int sc_sinceVer_QuantizeLinear = 21;
static const int sc_sinceVer_DequantizeLinear = 21;
static const int sc_sinceVer_Squeeze = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Squeeze' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Squeeze' can be computed at compile-time. Consider using constexpr (con.5).
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
static const int sc_sinceVer_QuantizeLinear = 21;
static const int sc_sinceVer_DequantizeLinear = 21;
static const int sc_sinceVer_Squeeze = 21;
static const int sc_sinceVer_Unsqueeze = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Unsqueeze' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Unsqueeze' can be computed at compile-time. Consider using constexpr (con.5).
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
static const int sc_sinceVer_DequantizeLinear = 21;
static const int sc_sinceVer_Squeeze = 21;
static const int sc_sinceVer_Unsqueeze = 21;
static const int sc_sinceVer_Reshape = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Reshape' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Reshape' can be computed at compile-time. Consider using constexpr (con.5).
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
static const int sc_sinceVer_Squeeze = 21;
static const int sc_sinceVer_Unsqueeze = 21;
static const int sc_sinceVer_Reshape = 21;
static const int sc_sinceVer_Cast = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Cast' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Cast' can be computed at compile-time. Consider using constexpr (con.5).
onnxruntime/core/providers/dml/OperatorAuthorHelper/OperatorVersions.h
static const int sc_sinceVer_Unsqueeze = 21;
static const int sc_sinceVer_Reshape = 21;
static const int sc_sinceVer_Cast = 21;
static const int sc_sinceVer_Shape = 21;

Check warning

Code scanning / PREfast

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Shape' can be computed at compile-time. Consider using constexpr (con.5). Warning

The const variable 'OperatorHelper::OnnxOperatorSet21::sc_sinceVer_Shape' can be computed at compile-time. Consider using constexpr (con.5).
@PatriceVignola
Copy link
Contributor Author

/azp run Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run ONNX Runtime Web CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows CPU CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU CUDA CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run orttraining-ortmodule-distributed

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run orttraining-linux-gpu-ci-pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

1 similar comment
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU TensorRT CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU Doc Gen CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run Windows GPU DML CI Pipeline

@PatriceVignola
Copy link
Contributor Author

/azp run Windows ARM64 QNN CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

1 similar comment
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@PatriceVignola
Copy link
Contributor Author

/azp run orttraining-linux-ci-pipeline

@PatriceVignola
Copy link
Contributor Author

/azp run Windows x64 QNN CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

1 similar comment
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

fdwr
fdwr previously approved these changes Aug 21, 2024
View reviewed changes
Copy link
Contributor

@fdwr fdwr left a comment

Choose a reason for hiding this comment

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

👍

@PatriceVignola PatriceVignola merged commit de6ebcb into main Aug 21, 2024
95 of 97 checks passed
@PatriceVignola PatriceVignola deleted the user/pavignol/add-int4-qdq branch August 21, 2024 06:44
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fdwr fdwr fdwr approved these changes

@smk2007 smk2007 Awaiting requested review from smk2007

@zhangxiang1993 zhangxiang1993 Awaiting requested review from zhangxiang1993

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@PatriceVignola @fdwr