Add LruFusionCache when direct bindings is used#2806
Open
rdspring1 wants to merge 4 commits intoLightning-AI:mainfrom
Open
Add LruFusionCache when direct bindings is used#2806rdspring1 wants to merge 4 commits intoLightning-AI:mainfrom
rdspring1 wants to merge 4 commits intoLightning-AI:mainfrom
Conversation
kshitij12345
approved these changes
Dec 18, 2025
Collaborator
kshitij12345
left a comment
There was a problem hiding this comment.
LGTM, thanks @rdspring1
| # by nvfuserex.py when nvFuser is available. | ||
|
|
||
| DIRECT_BINDINGS_SUPPORTED_VERSION = LooseVersion("0.2.34") | ||
| DIRECT_BINDINGS_SUPPORTED_VERSION = LooseVersion("0.2.35") |
Collaborator
There was a problem hiding this comment.
Is this the minimum version which ships with LruFusionCache?
| return func | ||
| from nvfuser_direct import LruFusionCache | ||
|
|
||
| return LruFusionCache(max_fusions=16384)(func) |
Collaborator
There was a problem hiding this comment.
Default value for max_fusions is 16384, we can remove this here.
Collaborator
There was a problem hiding this comment.
qq: will there be an option of setting cache size? Or it would not be that useful
Collaborator
Author
There was a problem hiding this comment.
Usually we pick a reasonable number to avoid out-of-memory issues. We never thought to change it at runtime.
crcrpar
approved these changes
Dec 19, 2025
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR enables an LRU Fusion Cache decorator for direct bindings to address issue #2700.
scale operations, which create non-trivial allocation domains.