Comments (1)
I can fix the extract slice ops to give correct shapes for the concat ops fairly quickly, but need to modify the structure of the lowering to account for the corner tiles taking on different values for each batch/channel (currently these are just paddings by a value like input[0,0,0,0] for the top-left corner), otherwise numerics mismatches would be reported.
from torch-mlir.
Related Issues (20)
- convert-torch-onnx-to-torch generates invalid IR for onnx.Resize where scaling is in the first two dimensions
- aten.pad with mode = reflect is lowered wrong (numeric mismatch)
- [ONNX] Expand more ONNX operators as functions when importing HOT 1
- tm_tensor.scatter op mismatch in shape of indices and update value HOT 3
- Failed to lower "torch.operator "onnx.Pad"" with axes parameter
- Compile torch.nn.functional.scaled_dot_product_attention failed HOT 3
- [TorchONNXToTorch] Bug in PadOp pad tensor rearrangement HOT 2
- Remove optional tensor logic from linalg lowering for `IndexPutHackedTwinOp`
- Failed to lower 'torch.aten.scatter_reduce.two' to stablehlo
- support torch.aten.diag HOT 4
- MLIR Python pass manager API will assert if the pass issues errors but does not signal failure
- Bump onnx to 1.16.1 HOT 2
- Need E2E ONNX op tests in CI HOT 7
- [ONNX] Bernoulli operator implementation might be wrong (value mismatch in e2e testing when using function expansion)
- Can't lower onnx.Pad with "wrap" mode HOT 1
- Error compiling MobilenetV2
- Support specialized lowering to depthwise_conv_2d_nchw_chw_q HOT 3
- One or more Stablehlo test(s) crashing after llvm bump to 266a5a9cb9daa96c1eeaebc18e10f5a37d638734 HOT 4
- Dtype checks failing with 'Subtraction, the `-` operator, with two bool tensors is not supported. Use the `^` or `logical_xor()` operator instead.'
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from torch-mlir.