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

Fail to generate forward.mlir for DeepLearning/Layers/FFN #165

Open
ShizhenWang2027 opened this issue Jan 15, 2025 · 0 comments
Open

Fail to generate forward.mlir for DeepLearning/Layers/FFN #165

ShizhenWang2027 opened this issue Jan 15, 2025 · 0 comments

Comments

@ShizhenWang2027
Copy link

Describe the bug
I tried the benchmark of DeepLearning/Layers/FFN but encountered a list index out of range problem as following:

Traceback (most recent call last):
File "/data/data5/szwang/workspace/NPUv2/buddy-benchmark/buddy-benchmark/benchmarks/DeepLearning/Layers/FFN/buddy_ffn_import.py", line 85, in
print(driver.construct_main_graph(True), file=module_file)
File "/data/data5/szwang/workspace/NPUv2/buddy-mlir/buddy-mlir/build/python_packages/buddy/compiler/graph/graph_driver.py", line 241, in construct_main_graph
return main_importer.import_main_graph()
File "/data/data5/szwang/workspace/NPUv2/buddy-mlir/buddy-mlir/build/python_packages/buddy/compiler/graph/graph.py", line 604, in import_main_graph
def generated_func(*args):
File "/data/data5/szwang/workspace/NPUv2/buddy-mlir/buddy-mlir/llvm/build/tools/mlir/python_packages/mlir_core/mlir/dialects/func.py", line 195, in decorator
return_values = f(*func_args, **func_kwargs)
File "/data/data5/szwang/workspace/NPUv2/buddy-mlir/buddy-mlir/build/python_packages/buddy/compiler/graph/graph.py", line 617, in generated_func
self._import_placeholder(node, args_list)
File "/data/data5/szwang/workspace/NPUv2/buddy-mlir/buddy-mlir/build/python_packages/buddy/compiler/graph/graph.py", line 668, in _import_placeholder
placeholder_name = args_list[self._num_input_visited]
IndexError: list index out of range
ninja: build stopped: subcommand failed.

To Reproduce
Just follow the instructions in benchmarks/DeepLearning/README.md.

Desktop (please complete the following information):

  • OS: [e.g. Ubuntu]
  • Version [e.g. 20.04]
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