Skip to content

[TLERaw] Remove Ruff Comments#338

Merged
sgjzfzzf merged 1 commit intotriton_v3.5.xfrom
triton_v3.5.x_jinjieliu
Feb 11, 2026
Merged

[TLERaw] Remove Ruff Comments#338
sgjzfzzf merged 1 commit intotriton_v3.5.xfrom
triton_v3.5.x_jinjieliu

Conversation

@sgjzfzzf
Copy link
Copy Markdown
Collaborator

@sgjzfzzf sgjzfzzf commented Feb 2, 2026

This PR is used to remove ‘noqa: F722’ in TLE-Raw development. Close #328.

@sgjzfzzf sgjzfzzf added this to the TLE-Raw Development milestone Feb 2, 2026
@sgjzfzzf sgjzfzzf added the enhancement New feature or request label Feb 2, 2026
@sgjzfzzf sgjzfzzf force-pushed the triton_v3.5.x_jinjieliu branch from 89293c7 to 43d08db Compare February 5, 2026 09:04
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
@sgjzfzzf sgjzfzzf force-pushed the triton_v3.5.x_jinjieliu branch 2 times, most recently from ccb0f82 to eba3e68 Compare February 11, 2026 03:27
@sgjzfzzf sgjzfzzf changed the title [Enhancement] Move Signature from Annotations to Decl [Enhancement] Remove Ruff Comments Feb 11, 2026
Copy link
Copy Markdown
Collaborator

@sunnycase sunnycase left a comment

Choose a reason for hiding this comment

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

LGTM

Copy link
Copy Markdown
Collaborator

@zhzhcookie zhzhcookie left a comment

Choose a reason for hiding this comment

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

LG

@sgjzfzzf sgjzfzzf changed the title [Enhancement] Remove Ruff Comments [TLERaw] Remove Ruff Comments Feb 11, 2026
@sgjzfzzf sgjzfzzf merged commit 7879d8b into triton_v3.5.x Feb 11, 2026
3 checks passed
@sgjzfzzf sgjzfzzf deleted the triton_v3.5.x_jinjieliu branch February 11, 2026 07:07
@sgjzfzzf sgjzfzzf restored the triton_v3.5.x_jinjieliu branch February 11, 2026 08:54
zhzhcookie pushed a commit that referenced this pull request Feb 27, 2026
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
sgjzfzzf added a commit that referenced this pull request Mar 6, 2026
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
sgjzfzzf added a commit that referenced this pull request Mar 9, 2026
* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
sunnycase pushed a commit that referenced this pull request Mar 9, 2026
* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
zhzhcookie pushed a commit that referenced this pull request Mar 11, 2026
* Add initial tle dist impl

* Add tle docs

* Implement submesh distributed barrier support in TLE

- Added support for submesh distributed barriers in the TLE dialect, allowing for more granular synchronization across submeshes.
- Introduced new attributes for the `DistributedBarrierOp` to handle group metadata, including `group_kind`, `group_rank`, `group_shape`, `group_axes`, and `group_mask`.
- Enhanced the `remote` function to validate and handle buffered tensors with appropriate metadata.
- Updated the `device_mesh` class to include launch shape and dimension names for better submesh handling.
- Implemented verification logic for the new attributes in `DistributedBarrierOp`.
- Added tests to ensure correct behavior of the new submesh barrier functionality and validation of remote buffered tensors.

* Add AxisInfoExt and RemotePointerUtils for Triton dialect enhancements

- Introduced AxisInfoExt.h and AxisInfoExt.cpp to extend axis information analysis with new visitors for LocalPointersOp and RemotePointersOp.
- Implemented RemotePointerUtils.h and RemotePointerUtils.cpp to handle remote pointer information extraction and inference of vector sizes/layouts.
- Added utility functions for managing remote pointer metadata and determining vectorization hints based on tensor properties.
- Enhanced axis analysis capabilities to support new Triton operations, improving optimization opportunities in the Triton dialect.

* Fix TLE local pointer encoding and retune fused launch params

* tle: add grid distributed barrier + optimize moe atomic fused

* remove tle docs from repo and ignore them

* ignore tle docs paths

* remove unintended triton_shared gitlink

* revert unnecessary cluster wait fence insertion

* refine markers and relocate tle alignment test

* Apply code-format changes

* restore core alignment test and split tle coverage

* update tle moe tuning and backend/lowering adjustments

* Apply code-format changes

* Fix

* [TLERaw] Revert `LLVM::CallOp`-Related Modification (#387)

* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* Apply code-format changes

* Update .gitignore to remove specific entries

Remove unnecessary files from .gitignore

* Clean up .gitignore by removing unused entries

Removed entries for Test and Agent from .gitignore

* Enhance TLE Support in TritonNVIDIAGPUToLLVM

- Added conditional compilation for TLE support in LoadStoreOpToLLVM.cpp, TargetInfo.cpp, TargetInfo.h, and TritonGPUToLLVM.cpp.
- Introduced new functions and modified existing ones to handle remote pointer information and shared memory access for TLE.
- Updated the TLE documentation to include examples for scalar shared-memory lookups and clarified the usage of local pointers.
- Ensured compatibility with both TLE and non-TLE builds by using preprocessor directives.

* Apply code-format changes

* Fix

* Refactor TLE-related code in TritonNVIDIAGPUToLLVM

- Removed unnecessary comments marking the beginning and end of TLE sections.
- Consolidated TLE-specific code under preprocessor directives to improve readability.
- Streamlined the inclusion of TLE headers and related logic in LoadStoreOpToLLVM, TargetInfo, and TritonGPUToLLVM files.
- Ensured consistent handling of shared and cluster shared pointers across various operations.
- Enhanced the clarity of cache policy handling in load and store operations.

* Apply code-format changes

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
Co-authored-by: flagtree-bot <flagtree_ai@163.com>
Co-authored-by: Jinjie Liu <jjliu@baai.ac.cn>
zhzhcookie pushed a commit that referenced this pull request Mar 13, 2026
Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
zhzhcookie pushed a commit that referenced this pull request Mar 13, 2026
* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
zhzhcookie pushed a commit that referenced this pull request Mar 13, 2026
* Add initial tle dist impl

* Add tle docs

* Implement submesh distributed barrier support in TLE

- Added support for submesh distributed barriers in the TLE dialect, allowing for more granular synchronization across submeshes.
- Introduced new attributes for the `DistributedBarrierOp` to handle group metadata, including `group_kind`, `group_rank`, `group_shape`, `group_axes`, and `group_mask`.
- Enhanced the `remote` function to validate and handle buffered tensors with appropriate metadata.
- Updated the `device_mesh` class to include launch shape and dimension names for better submesh handling.
- Implemented verification logic for the new attributes in `DistributedBarrierOp`.
- Added tests to ensure correct behavior of the new submesh barrier functionality and validation of remote buffered tensors.

* Add AxisInfoExt and RemotePointerUtils for Triton dialect enhancements

- Introduced AxisInfoExt.h and AxisInfoExt.cpp to extend axis information analysis with new visitors for LocalPointersOp and RemotePointersOp.
- Implemented RemotePointerUtils.h and RemotePointerUtils.cpp to handle remote pointer information extraction and inference of vector sizes/layouts.
- Added utility functions for managing remote pointer metadata and determining vectorization hints based on tensor properties.
- Enhanced axis analysis capabilities to support new Triton operations, improving optimization opportunities in the Triton dialect.

* Fix TLE local pointer encoding and retune fused launch params

* tle: add grid distributed barrier + optimize moe atomic fused

* remove tle docs from repo and ignore them

* ignore tle docs paths

* remove unintended triton_shared gitlink

* revert unnecessary cluster wait fence insertion

* refine markers and relocate tle alignment test

* Apply code-format changes

* restore core alignment test and split tle coverage

* update tle moe tuning and backend/lowering adjustments

* Apply code-format changes

* Fix

* [TLERaw] Revert `LLVM::CallOp`-Related Modification (#387)

* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* Apply code-format changes

* Update .gitignore to remove specific entries

Remove unnecessary files from .gitignore

* Clean up .gitignore by removing unused entries

Removed entries for Test and Agent from .gitignore

* Enhance TLE Support in TritonNVIDIAGPUToLLVM

- Added conditional compilation for TLE support in LoadStoreOpToLLVM.cpp, TargetInfo.cpp, TargetInfo.h, and TritonGPUToLLVM.cpp.
- Introduced new functions and modified existing ones to handle remote pointer information and shared memory access for TLE.
- Updated the TLE documentation to include examples for scalar shared-memory lookups and clarified the usage of local pointers.
- Ensured compatibility with both TLE and non-TLE builds by using preprocessor directives.

* Apply code-format changes

* Fix

* Refactor TLE-related code in TritonNVIDIAGPUToLLVM

- Removed unnecessary comments marking the beginning and end of TLE sections.
- Consolidated TLE-specific code under preprocessor directives to improve readability.
- Streamlined the inclusion of TLE headers and related logic in LoadStoreOpToLLVM, TargetInfo, and TritonGPUToLLVM files.
- Ensured consistent handling of shared and cluster shared pointers across various operations.
- Enhanced the clarity of cache policy handling in load and store operations.

* Apply code-format changes

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
Co-authored-by: flagtree-bot <flagtree_ai@163.com>
Co-authored-by: Jinjie Liu <jjliu@baai.ac.cn>
sunnycase pushed a commit that referenced this pull request Mar 17, 2026
* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
sunnycase added a commit that referenced this pull request Mar 17, 2026
* Add initial tle dist impl

* Add tle docs

* Implement submesh distributed barrier support in TLE

- Added support for submesh distributed barriers in the TLE dialect, allowing for more granular synchronization across submeshes.
- Introduced new attributes for the `DistributedBarrierOp` to handle group metadata, including `group_kind`, `group_rank`, `group_shape`, `group_axes`, and `group_mask`.
- Enhanced the `remote` function to validate and handle buffered tensors with appropriate metadata.
- Updated the `device_mesh` class to include launch shape and dimension names for better submesh handling.
- Implemented verification logic for the new attributes in `DistributedBarrierOp`.
- Added tests to ensure correct behavior of the new submesh barrier functionality and validation of remote buffered tensors.

* Add AxisInfoExt and RemotePointerUtils for Triton dialect enhancements

- Introduced AxisInfoExt.h and AxisInfoExt.cpp to extend axis information analysis with new visitors for LocalPointersOp and RemotePointersOp.
- Implemented RemotePointerUtils.h and RemotePointerUtils.cpp to handle remote pointer information extraction and inference of vector sizes/layouts.
- Added utility functions for managing remote pointer metadata and determining vectorization hints based on tensor properties.
- Enhanced axis analysis capabilities to support new Triton operations, improving optimization opportunities in the Triton dialect.

* Fix TLE local pointer encoding and retune fused launch params

* tle: add grid distributed barrier + optimize moe atomic fused

* remove tle docs from repo and ignore them

* ignore tle docs paths

* remove unintended triton_shared gitlink

* revert unnecessary cluster wait fence insertion

* refine markers and relocate tle alignment test

* Apply code-format changes

* restore core alignment test and split tle coverage

* update tle moe tuning and backend/lowering adjustments

* Apply code-format changes

* Fix

* [TLERaw] Revert `LLVM::CallOp`-Related Modification (#387)

* [TLERaw] revert llvm::CallOp related codes

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* [TLERaw] enable topk tle in ci

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* remove flake8 comments (#338)

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>

* Apply code-format changes

* Update .gitignore to remove specific entries

Remove unnecessary files from .gitignore

* Clean up .gitignore by removing unused entries

Removed entries for Test and Agent from .gitignore

* Enhance TLE Support in TritonNVIDIAGPUToLLVM

- Added conditional compilation for TLE support in LoadStoreOpToLLVM.cpp, TargetInfo.cpp, TargetInfo.h, and TritonGPUToLLVM.cpp.
- Introduced new functions and modified existing ones to handle remote pointer information and shared memory access for TLE.
- Updated the TLE documentation to include examples for scalar shared-memory lookups and clarified the usage of local pointers.
- Ensured compatibility with both TLE and non-TLE builds by using preprocessor directives.

* Apply code-format changes

* Fix

* Refactor TLE-related code in TritonNVIDIAGPUToLLVM

- Removed unnecessary comments marking the beginning and end of TLE sections.
- Consolidated TLE-specific code under preprocessor directives to improve readability.
- Streamlined the inclusion of TLE headers and related logic in LoadStoreOpToLLVM, TargetInfo, and TritonGPUToLLVM files.
- Ensured consistent handling of shared and cluster shared pointers across various operations.
- Enhanced the clarity of cache policy handling in load and store operations.

* Apply code-format changes

---------

Signed-off-by: Jinjie Liu <jjliu@baai.ac.cn>
Co-authored-by: flagtree-bot <flagtree_ai@163.com>
Co-authored-by: Jinjie Liu <jjliu@baai.ac.cn>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants