Dump nodes with potential overflow in half conversion (#23363)
Add a tool to generate node_block_list used in [float16 conversion tool](https://github.com/microsoft/onnxruntime/blob/04030f64be10e020d3ac9aa5ba7d0f2917cbd14e/onnxruntime/python/tools/transformers/float16.py#L175).
Previously, we have a feature to dump statistics data (like min, max) of
each node input/output. However, it is time consuming to generate a list
of nodes that need to be kept in float32 when model is large.
This could help speed up the process by outputting a list of nodes that
have potential overflow in float-to-half conversion.
Usage is to build onnxruntime from source with ` --cmake_extra_defines
onnxruntime_DEBUG_NODE_INPUTS_OUTPUTS=1`, then set some environment
variables before running float32 optimized onnx model like:
```
export ORT_DEBUG_NODE_IO_DUMP_HALF_CONVERSION_OVERFLOW=1
export ORT_DEBUG_NODE_IO_HALF_OVERFLOW_THRESHOLD=50000
python benchmark.py -e optimum --height 1024 --width 1024 --steps 3 -b 1 -v Flux.1D -p flux1_dev_onnx/fp32_opt --skip_warmup
```
The threshold `ORT_DEBUG_NODE_IO_HALF_OVERFLOW_THRESHOLD` shall be <=
65504. The default value is 50000 if the environment variable is not
set. It is better to leave some margin if number of samples are not
large enough in the test.
As a demo, we add an option --skip_warmup to benchmark.py for Flux, so
that we can reduce the time on dumping warm-up runs.
Example snippet of stdout (each inference session has such a summary
when session ended):
```
Total counter in node dumping: 141
Found 2 nodes cannot be converted to half precision due to potential input/output overflow.
Operator frequencies for these nodes:
Softmax : 1
MatMul : 1
# -------
# Example python script for float16 conversion
# For details, search `node_block_list` in https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/float16.py
# -------
from onnxruntime.transformers.onnx_model import OnnxModel
m = OnnxModel(onnx.load('flux1_dev_onnx/fp32_opt/vae_decoder/model.onnx'))
node_block_list = [
'/decoder/mid_block/attentions.0/Softmax',
'/decoder/mid_block/attentions.0/MatMul',
]
m.convert_float_to_float16(keep_io_types=False, node_block_list=node_block_list)
m.save_model_to_file('fp16/optimized.onnx', use_external_data_format=False)
```
Then you can use the python script to convert corresponding model to
float16.
### Motivation and Context
It is a tool used to generate node_block_list used in float16 conversion
of stable diffusion 3.x and flux models in
https://github.com/microsoft/onnxruntime/pull/22986.
In stable diffusion or Flux pipeline, there are multiple models and
there could be multiple session runs for each model. Without a proper
tool, it is time consuming to get node_block_list for each model.
onnxruntime
5735e1bc - Dump nodes with potential overflow in half conversion (#23363)
