Skip to content
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

crash for the use of onnx.Multinomial #854

Open
pdhirajkumarprasad opened this issue Sep 27, 2024 · 0 comments
Open

crash for the use of onnx.Multinomial #854

pdhirajkumarprasad opened this issue Sep 27, 2024 · 0 comments

Comments

@pdhirajkumarprasad
Copy link

for the given IR

module {
  func.func @"torch-jit-export"( %arg6: !torch.vtensor<[?,4],f32>) -> (!torch.vtensor<[?,1],si64>) attributes {torch.onnx_meta.ir_version = 6 : si64, torch.onnx_meta.opset_version = 21 : si64, torch.onnx_meta.producer_name = "pytorch", torch.onnx_meta.producer_version = "1.7"} {
    %82 = torch.operator "onnx.Multinomial"(%arg6) {torch.onnx.dtype = 7 : si64, torch.onnx.sample_size = 1 : si64} : (!torch.vtensor<[?,4],f32>) -> !torch.vtensor<[?,1],si64> 
    return %82: !torch.vtensor<[?,1],si64>
  }
}

seeing crash as

PLEASE submit a bug report to https://github.com/llvm/llvm-project/issues/ and include the crash backtrace.
Stack dump:
0.	Program arguments: torch-mlir-opt --convert-torch-onnx-to-torch --torch-decompose-complex-ops -torch-backend-to-linalg-on-tensors-backend-pipeline t1.mlir
#0 0x0000564d19bf5060 llvm::sys::PrintStackTrace(llvm::raw_ostream&, int) (/proj/xhdhdstaff6/dhirajp/localBuild/torch-mlir/build/bin/torch-mlir-opt+0x1603060)
#1 0x0000564d19bf298e SignalHandler(int) Signals.cpp:0:0
#2 0x00007f333dfee520 (/lib/x86_64-linux-gnu/libc.so.6+0x42520)
#3 0x0000564d1baf4620 
Segmentation fault (core dumped)

command:

torch-mlir-opt -split-input-file -verify-diagnostics -convert-torch-onnx-to-torch t1.mlir
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant