mirror of
https://github.com/huggingface/diffusers.git
synced 2025-12-06 12:34:13 +08:00
e6639fef70
* start overhauling the benchmarking suite. * fixes * fixes * checking. * checking * fixes. * error handling and logging. * add flops and params. * add more models. * utility to fire execution of all benchmarking scripts. * utility to push to the hub. * push utility improvement * seems to be working. * okay * add torchprofile dep. * remove total gpu memory * fixes * fix * need a big gpu * better * what's happening. * okay * separate requirements and make it nightly. * add db population script. * update secret name * update secret. * population db update * disable db population for now. * change to every monday * Update .github/workflows/benchmark.yml Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com> * quality improvements. * reparate hub upload step. * repository * remove csv * check * update * update * threading. * update * update * updaye * update * update * update * remove peft dep * upgrade runner. * fix * fixes * fix merging csvs. * push dataset to the Space repo for analysis. * warm up. * add a readme * Apply suggestions from code review Co-authored-by: Luc Georges <McPatate@users.noreply.github.com> * address feedback * Apply suggestions from code review * disable db workflow. * update to bi weekly. * enable population * enable * updaye * update * metadata * fix --------- Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com> Co-authored-by: Luc Georges <McPatate@users.noreply.github.com>
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
from functools import partial
|
|
|
|
import torch
|
|
from benchmarking_utils import BenchmarkMixin, BenchmarkScenario, model_init_fn
|
|
|
|
from diffusers import UNet2DConditionModel
|
|
from diffusers.utils.testing_utils import torch_device
|
|
|
|
|
|
CKPT_ID = "stabilityai/stable-diffusion-xl-base-1.0"
|
|
RESULT_FILENAME = "sdxl.csv"
|
|
|
|
|
|
def get_input_dict(**device_dtype_kwargs):
|
|
# height: 1024
|
|
# width: 1024
|
|
# max_sequence_length: 77
|
|
hidden_states = torch.randn(1, 4, 128, 128, **device_dtype_kwargs)
|
|
encoder_hidden_states = torch.randn(1, 77, 2048, **device_dtype_kwargs)
|
|
timestep = torch.tensor([1.0], **device_dtype_kwargs)
|
|
added_cond_kwargs = {
|
|
"text_embeds": torch.randn(1, 1280, **device_dtype_kwargs),
|
|
"time_ids": torch.ones(1, 6, **device_dtype_kwargs),
|
|
}
|
|
|
|
return {
|
|
"sample": hidden_states,
|
|
"encoder_hidden_states": encoder_hidden_states,
|
|
"timestep": timestep,
|
|
"added_cond_kwargs": added_cond_kwargs,
|
|
}
|
|
|
|
|
|
if __name__ == "__main__":
|
|
scenarios = [
|
|
BenchmarkScenario(
|
|
name=f"{CKPT_ID}-bf16",
|
|
model_cls=UNet2DConditionModel,
|
|
model_init_kwargs={
|
|
"pretrained_model_name_or_path": CKPT_ID,
|
|
"torch_dtype": torch.bfloat16,
|
|
"subfolder": "unet",
|
|
},
|
|
get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
|
|
model_init_fn=model_init_fn,
|
|
compile_kwargs={"fullgraph": True},
|
|
),
|
|
BenchmarkScenario(
|
|
name=f"{CKPT_ID}-layerwise-upcasting",
|
|
model_cls=UNet2DConditionModel,
|
|
model_init_kwargs={
|
|
"pretrained_model_name_or_path": CKPT_ID,
|
|
"torch_dtype": torch.bfloat16,
|
|
"subfolder": "unet",
|
|
},
|
|
get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
|
|
model_init_fn=partial(model_init_fn, layerwise_upcasting=True),
|
|
),
|
|
BenchmarkScenario(
|
|
name=f"{CKPT_ID}-group-offload-leaf",
|
|
model_cls=UNet2DConditionModel,
|
|
model_init_kwargs={
|
|
"pretrained_model_name_or_path": CKPT_ID,
|
|
"torch_dtype": torch.bfloat16,
|
|
"subfolder": "unet",
|
|
},
|
|
get_model_input_dict=partial(get_input_dict, device=torch_device, dtype=torch.bfloat16),
|
|
model_init_fn=partial(
|
|
model_init_fn,
|
|
group_offload_kwargs={
|
|
"onload_device": torch_device,
|
|
"offload_device": torch.device("cpu"),
|
|
"offload_type": "leaf_level",
|
|
"use_stream": True,
|
|
"non_blocking": True,
|
|
},
|
|
),
|
|
),
|
|
]
|
|
|
|
runner = BenchmarkMixin()
|
|
runner.run_bencmarks_and_collate(scenarios, filename=RESULT_FILENAME)
|