gpt2tosainferenceBug

gpt2tosainferenceBug.txt

➜  SHARK git:(gpt) ✗ python tank/pytorch/gpt2/gpt2.py
Torch Golden Result:  tensor([[[ -31.8388,  -30.9854,  -34.4231,  ...,  -39.7515,  -38.6848,
           -32.3074],
         [ -99.2055,  -98.8202, -104.2251,  ..., -112.2020, -109.0224,
          -100.2584],
         [-115.6919, -116.9150, -119.1486,  ..., -124.9616, -123.2126,
          -116.6671],
         [-123.0994, -123.1445, -128.7349,  ..., -130.6248, -130.6557,
          -125.1285],
         [ -80.2680,  -81.8277,  -89.0646,  ...,  -94.5047,  -96.1721,
           -83.7583]]], grad_fn=<UnsafeViewBackward0>)
/home/chi/src/ubuntu20/shark/SHARK/shark.venv/lib/python3.10/site-packages/torch/jit/_check.py:181: UserWarning: The TorchScript type system doesn't support instance-level annotations on empty non-base types in `__init__`. Instead, either 1) use a type annotation in the class body, or 2) wrap the type in `torch.jit.Attribute`.
  warnings.warn("The TorchScript type system doesn't support "
/home/chi/src/ubuntu20/shark/SHARK/shark.venv/lib/python3.10/site-packages/torch/jit/_trace.py:744: UserWarning: The input to trace is already a ScriptModule, tracing it is a no-op. Returning the object as is.
  warnings.warn(
Target triple found:x86_64-linux-gnu
Traceback (most recent call last):
  File "/home/chi/src/ubuntu20/shark/SHARK/tank/pytorch/gpt2/gpt2.py", line 115, in <module>
    shark_module.compile()
  File "/home/chi/src/ubuntu20/shark/SHARK/shark/shark_inference.py", line 93, in compile
    self.shark_runner = SharkRunner(
  File "/home/chi/src/ubuntu20/shark/SHARK/shark/shark_runner.py", line 84, in __init__
    ) = get_iree_compiled_module(
  File "/home/chi/src/ubuntu20/shark/SHARK/shark/iree_utils/compile_utils.py", line 125, in get_iree_compiled_module
    flatbuffer_blob = compile_module_to_flatbuffer(
  File "/home/chi/src/ubuntu20/shark/SHARK/shark/iree_utils/compile_utils.py", line 88, in compile_module_to_flatbuffer
    flatbuffer_blob = ireec.compile_str(
  File "/home/chi/src/ubuntu20/shark/SHARK/shark.venv/lib/python3.10/site-packages/iree/compiler/tools/core.py", line 277, in compile_str
    result = invoke_immediate(cl, immediate_input=input_bytes)
  File "/home/chi/src/ubuntu20/shark/SHARK/shark.venv/lib/python3.10/site-packages/iree/compiler/tools/binaries.py", line 194, in invoke_immediate
    process = subprocess.run(command_line, capture_output=True, **run_args)
  File "/usr/lib/python3.10/subprocess.py", line 503, in run
    stdout, stderr = process.communicate(input, timeout=timeout)
  File "/usr/lib/python3.10/subprocess.py", line 1152, in communicate
    stdout, stderr = self._communicate(input, endtime, timeout)
  File "/usr/lib/python3.10/subprocess.py", line 1983, in _communicate
    input_view = memoryview(self._input)
TypeError: memoryview: a bytes-like object is required, not 'torch_mlir._mlir_libs._mlir.ir.Module'
➜  SHARK git:(gpt) ✗