CANN: fix acl_tensor_ptr usage in ASCEND_310P ROPE #17347
Merged
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
Fix compilation errors in the ASCEND_310P-specific ROPE operation code by adding .get() calls when passing acl_tensor_ptr smart pointers to functions expecting raw aclTensor* pointers. This fixes the code that was missed in the previous refactoring commit (8981848) which changed ggml_cann_create_tensor() return type from aclTensor* to acl_tensor_ptr.
Collaborator
|
Thanks for you patch. Verified on 310 devices. |
hipudding
approved these changes
Nov 18, 2025
Collaborator
hipudding
left a comment
hipudding
left a comment
There was a problem hiding this comment.
Please format these code changes.
github-actions
bot
added
the
ggml
Collaborator
Author
Thanks for the reminder! I’ve formatted the code. |
Collaborator
|
This change is only related to the CANN backend. Given the tight CI resources, we are merging this fix to resolve the issue as quickly as possible. |
ronaldmannak
pushed a commit
to PicoMLX/llama.cpp
that referenced
this pull request
Nov 19, 2025
* cann: fix acl_tensor_ptr usage in ASCEND_310P ROPE implementation Fix compilation errors in the ASCEND_310P-specific ROPE operation code by adding .get() calls when passing acl_tensor_ptr smart pointers to functions expecting raw aclTensor* pointers. This fixes the code that was missed in the previous refactoring commit (8981848) which changed ggml_cann_create_tensor() return type from aclTensor* to acl_tensor_ptr. * cann: format code
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Outdated suggestions cannot be applied.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.
Fix compilation errors in the ASCEND_310P-specific ROPE operation code by adding .get() calls when passing acl_tensor_ptr smart pointers to functions expecting raw aclTensor* pointers.
This fixes the code that was missed in the previous refactoring commit (8981848) which changed ggml_cann_create_tensor() return type from aclTensor* to acl_tensor_ptr.