Warming JIT up with 10 runs
Running JIT 100 times
Done benchmarking JIT
Tracing model with TVM
Warming TVM up with 10 iters
Traceback (most recent call last):
File "test/benchmarks.py", line 82, in <module>
run_benchmark(csv_file)
File "test/benchmarks.py", line 75, in run_benchmark
benchmark(model, csv_file)
File "test/benchmarks.py", line 44, in benchmark
_ = trace_tvm(*inputs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 539, in __call__
result = self.forward(*input, **kwargs)
RuntimeError: _Map_base::at
The above operation failed in interpreter.
Traceback (most recent call last):
python3 test/benchmarks.py
output:
packages: