Skip to content

issues Search Results · repo:llvm/torch-mlir language:C++

Filter by

744 results
 (48 ms)

744 results

inllvm/torch-mlir (press backspace or delete to remove)

llvm/torch-mlir
testcase failing due to commit 7b23a1f5d87064daded4b89487dc968fd933051e

The following commit (https://github.com/llvm/torch-mlir/commit/7b23a1f5d87064daded4b89487dc968fd933051e) has caused the testcase failure: https://github.com/iree-org/iree-test-suites/tree/main/onnx_ops/onnx/node/generated/test_averagepool_2d_ceil/ ...
  • amd-vivekag
  • 1
  • Opened 
    2 days ago
  • #4079

llvm/torch-mlir
Error when running build_tools/update_torch_ods.sh

When I run build_tools/update_torch_ods.sh I get this error `ERROR: Op does not match any Torch ops in Registry Given op: aten::stft : (Tensor, int, int?, int?, Tensor?, bool, bool?, bool?, bool?) ...
  • AnaT246
  • 1
  • Opened 
    3 days ago
  • #4077

llvm/torch-mlir
properly handle non-standard bias quantization in FuseQuantizedOps

IR as seen in https://github.com/iree-org/iree/issues/19416 generates numerical accuracy errors, since the bias is not quantized with a scale equal to input_scale*weight_scale, which is tacitly assumed ...
  • zjgarvey
  • Opened 
    10 days ago
  • #4059

llvm/torch-mlir
Improve onnx_exporter locations

  • rkayaith
  • Opened 
    10 days ago
  • #4058

llvm/torch-mlir
Python tests are failing in Windows build

There are two types of failures when running the python based tests on Windows: 1. End-to-end execution tests are failing due to the signal.SIGALRM (used for timeout handling in the following piece ...
  • sahas3
  • Opened 
    14 days ago
  • #4040

llvm/torch-mlir
Trouble building the project

Hello, I watched the presentation An introduction to Torch-MLIR at FOSDEM 25 and decided to give it a try. I made a good effort, including building MLIR itself from source, since mlir-tblgen does not ...
  • smanilov
  • 4
  • Opened 
    14 days ago
  • #4038

llvm/torch-mlir
torch.cond operator not supported on a simple example

Issue : Trying to implement in a neural network a logic that routes dynamically a sample based on some condition. I built a dummy example of how the network should look like and I would like to export ...
  • JibAxelera
  • 6
  • Opened 
    19 days ago
  • #4028

llvm/torch-mlir
Fails to legalize operation 'torch.aten.convolution' when output_type=OutputType.TOSA

Reproducible code: import torch import torch.nn as nn import torch_mlir from torch_mlir import TensorPlaceholder, OutputType class conv1d(nn.Module): def __init__(self): super(conv1d, self).__init__() ...
  • KunWillRICH
  • 1
  • Opened 
    20 days ago
  • #4026

llvm/torch-mlir
Make building TOSA support optional

Similar components in torch-mlir are already optional: https://github.com/llvm/torch-mlir/blob/a9a1355c98caddf30b220755b558f01fa1e5ee05/CMakeLists.txt#L37-L45 This would allow downstream projects that ...
  • ScottTodd
  • Opened 
    25 days ago
  • #4019

llvm/torch-mlir
LLVM ERROR: pattern '(anonymous namespace)::AdjustCallingConventionForReturn' does not support 1:N conversion

There s an error with this code torch-mlir-opt -pass-pipeline= builtin.module(torchscript-module-to-torch-backend-pipeline) ~/tmp/torch_raw.mlir | tee ~/tmp/torch.mlir This is the torch_raw.mlir file: ...
  • AnaT246
  • 2
  • Opened 
    25 days ago
  • #4018
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub