[FEAT] Triton v3.5.x hint manager #349
Open
+216
−24
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Summary
This PR migrates the HintManager architecture to the v3.5.x branch. It decouples backend logic from the core compiler, enabling cleaner support for NVIDIA and Ascend backends without polluting the main codebase.
Key Changes
Architecture: Introduced HintManager and BaseHintHandler to manage backend-specific logic via a standardized hook mechanism.
Decoupling: Refactored CodeGenerator.py and jit.py by replacing hardcoded if backend == ... checks with generic hint_trigger calls.
NVIDIA Support: Added NvidiaHintHandler to handle backend-specific logic (e.g., tl.load hints), separating invocation logic from core infrastructure changes.
Optimization: Implemented lazy loading for handlers to avoid circular imports and standardized source code comment parsing.