forked from llvm/torch-mlir
-
Notifications
You must be signed in to change notification settings - Fork 6
[AutoBump] Merge with 7b8d0bdb (Feb 13) (7) #594
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
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
Added required but missing Shape inference for `aten.prod`
``` [build] D:\dev\projects\iree\third_party\torch-mlir\lib\Conversion\TorchToTosa\TorchToTosa.cpp(3498): warning C4305: 'argument': truncation from 'double' to 'const T' [build] with [build] [ [build] T=float [build] ] [build] D:\dev\projects\iree\third_party\torch-mlir\lib\Conversion\TorchToTosa\TorchToTosa.cpp(3504): warning C4305: 'argument': truncation from 'double' to 'const T' [build] with [build] [ [build] T=float [build] ] ``` (Not sure why the half/one/three lines were warning free, might as well fix them too.
Partially resolves llvm#3453 by introducing better error reporting for unsupported configurations in the `onnx.Resize` lowering.
Uses `llvm_unreachable` to mark path unreachable to fix compiler error ``` DefaultDomainQtoZ.cpp:194:1: error: non-void function does not return a value in all control paths ``` Signed-off-by: Ian Wood <[email protected]>
Fixes iree-org/iree-turbine#281. **_TL;DR:_** The `weakref.finalize` objects cause the model parameters to be kept in memory in-between consecutive `aot.export` calls in the same process. We remove them to enable releasing the memory, this does not change the behavior of `RefTracker` or `RefMapping` classes anyhow else. Signed-off-by: Ege Beysel <[email protected]>
I fixed two calls to yaml.load to explicitly use the Safe Loader. I copied the code from other repos that do it this way.
Fixes llvm#4019. --------- Signed-off-by: Benoit Jacob <[email protected]>
Addresses an issue introduced by <llvm#3945> in an external test suite.
Follows llvm#4021. Also pushes a small pre-commit fix. Bazel CI triggered here: https://github.com/sjain-stanford/torch-mlir/actions/runs/13297425038/job/37132415527
mgehre-amd
approved these changes
Jul 2, 2025
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.
No description provided.