CANN: Support eager execution mode under ACL graph compilation #15712
+16
−1
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
github-actions
bot
added
documentation
hipudding
reviewed
Sep 1, 2025
docs/backend/CANN.md
Outdated
|
|
||
| Converting the matmul weight format from ND to NZ can significantly improve performance on the 310I DUO NPU. | ||
|
|
||
| ### GGML_CANN_EAGER_MODE |
There was a problem hiding this comment.
I think it's better called GGML_CANN_ACL_GRAPH or some name like that. Default enable acl graph for perfermance.
There was a problem hiding this comment.
Good idea! I think when compiling with ACL graph support, ACL graph should be enabled by default, and we use GGML_CANN_DISABLE_ACL_GRAPH to disable it. Would that be more appropriate?
hipudding
changed the title
Add support for running operators in eager mode while ACL graph compilation is enabled. This allows bypassing graph execution and directly submitting ops, which is useful for debugging and reducing graph build overhead in certain scenarios. Signed-off-by: noemotiovon <[email protected]>
Signed-off-by: noemotiovon <[email protected]>
Signed-off-by: noemotiovon <[email protected]>
noemotiovon
force-pushed
the
eager_mode
branch
from
dc17a42 to
195674a
Compare
hipudding
approved these changes
Sep 2, 2025
walidbr
pushed a commit
to walidbr/llama.cpp
that referenced
this pull request
Sep 7, 2025
…org#15712) * [CANN] Support eager execution mode under ACL graph compilation Add support for running operators in eager mode while ACL graph compilation is enabled. This allows bypassing graph execution and directly submitting ops, which is useful for debugging and reducing graph build overhead in certain scenarios. Signed-off-by: noemotiovon <[email protected]> * fix typo Signed-off-by: noemotiovon <[email protected]> * rename to acl_graph_mode Signed-off-by: noemotiovon <[email protected]> --------- Signed-off-by: noemotiovon <[email protected]>
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.
Add support for running operators in eager mode while ACL graph compilation is enabled. This allows bypassing graph execution and directly submitting ops, which is useful for debugging and reducing graph build overhead in certain scenarios.
Make sure to read the contributing guidelines before submitting a PR