[AutoBump] Merge with 0913b967 (Nov 22) (120) #510
Merged
Conversation
This file contains 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
…shape calculation of `upsample_nearest2d`) (llvm#3764) As per title. See also [PR](llvm#3750) for `torch.aten.mul.float_int`. --------- Co-authored-by: zjgarvey <[email protected]>
…lvm#3887) Addresses a bug when trying to materialize a non fp64 attr to a constant float op in scalarize shapes.
Fixes nod-ai/SHARK-ModelDev#888 If stash_type is different from input_dtype/result_dtype: 1. convert x dtype to stash_type 2. calculate mean and var in stash_type since x is in stash_type already 3. convert back to result_dtype before stage two calculation 4. convert mean_dtype and var_dtype if they are different from stash_type e2e test added in nod-ai/SHARK-TestSuite#399
TODO: support multiple batches and classes
…rsion to Arith. (llvm#3750) Folder is required to simplify the shape calculation of `torch.aten.__interpolate.size_list_scale_list`: https://github.com/llvm/torch-mlir/blob/5eab669c4ab0c3aab3dab5b95d0172ab0a8395b8/lib/Dialect/Torch/Transforms/AbstractInterpLibrary.cpp#L6900-L6907 (I've re-run `build_tools/update_abstract_interp_lib.sh`) --------- Co-authored-by: zjgarvey <[email protected]>
- Add `AtenFftRfftOp` to Torch dialect. - Add conversion of `AtenFftRfftOp` to Linalg, using a `linalg.matmul` per output component (real and imaginary). Computing the DFT is _O(n^2)_. - Add decomposition of `AtenFftRfftOp` into Torch-level ops (same paradigm as above). - Add unit and end-to-end tests.
Fixes `onnx.Pow(float,int)` and `Pow(int,float)` accuracy. Torch uses `double` internally to compute pow if one argument is integer and the other one is floating point (due to C++ promotion rules). This PR keeps `onnx.Pow(int,int)` as is, which still produces numeric mismatches for values that overflow. torch uses a pure-integer implementation, where torch-mlir currently maps it to `Pow(float,float)`
…isc (llvm#3886) - Add Torch to TOSA lowering for the following ops: + torch.aten.upsample_nearest2d + torch.aten.upsample_nearest2d.vec + torch.aten.outer + torch.prims.split_dim - Add Tanh approximation mode for GELU lowering - Add different types support for compare ops - Add different input and output types support for linalg vector norm lowering - Update xfail with new e2e results - Add new LIT tests to basic.mlir Change-Id: I7b1d44d94319cf94fcc9d234cc07708ef9ce321e Signed-off-by: Justin Ngo <[email protected]>
[AutoBump] Merge with fixes of 8711d3e (Dec 02) (126)
cferry-AMD
approved these changes
Feb 6, 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.