[ascend] refactor code #4176
Draft
[ascend] refactor code #4176
+93
−169
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
jinminxi104
reviewed
Dec 4, 2025
jinminxi104
reviewed
Dec 4, 2025
| AscendOpsBackend.enable_graph = ascend_graph_runner.enable_graph | ||
| return ascend_graph_runner | ||
| from lmdeploy.pytorch.backends.cuda.graph_runner import CUDAGraphRunner | ||
| return CUDAGraphRunner(model, model_config, cache_config, backend_config, device) |
Collaborator
There was a problem hiding this comment.
let's make a new aclgraphrunner instead
Contributor
There was a problem hiding this comment.
Pull request overview
This PR refactors the Ascend backend code by removing Ascend310P-specific support and simplifying the codebase to focus solely on Ascend910 devices. The refactoring also restructures the update_step_context method for better code organization.
Key changes:
- Removed all Ascend310P-specific logic including NZ format weight transformations, block shape calculations, and attention mask handling
- Simplified
SocVersionclass by replacing the cacheddevice_name()method with a class attribute - Refactored
update_step_contextmethod to use helper functions for better code organization and readability
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.
| File | Description |
|---|---|
| lmdeploy/pytorch/backends/dlinfer/linear.py | Removed Ascend310P-specific weight transformation logic for NZ format |
| lmdeploy/pytorch/backends/dlinfer/ascend/op_backend.py | Removed Ascend310P support from block shape methods, simplified SocVersion class, refactored update_step_context with helper functions, removed enable_aclgraph method, updated build_graph_runner to use only CUDAGraphRunner, removed Ascend310P compile mode settings |
| lmdeploy/pytorch/backends/dlinfer/ascend/graph_runner.py | Removed Ascend310P-specific get_logits compilation logic |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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.
No description provided.