Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: Vysarat

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Differential Revision: D61883224

Summary:

X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Differential Revision: D61883224

Summary:

X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:

X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/pytorch#136838


For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Reviewed By: dbort

Differential Revision: D61883224

Summary:

X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Reviewed By: dbort

Differential Revision: D61883224

Summary:

X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Reviewed By: dbort

Differential Revision: D61883224

Summary:
X-link: pytorch/executorch#5720

For smaller models the overhead of profiling ops might be prohibitively large (distorting the inference execution time significantly) so we provide users an option to disable op profiling and essentially only profile the important events such as inference execution time.

To disable operator profiling users need to do:
```
etdump_gen.set_event_tracer_profiling_level(executorch::runtime::EventTracerProfilingLevel::kNoOperatorProfiling);
```

Test Plan: Added test case.

Differential Revision: D61883224

Pull Request resolved: #136838
Approved by: https://github.com/dbort