mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-10-25 06:43:41 +08:00
Keval Morabia
1ccd945a51
`cuda-python` has mixed license and needs EStaff approval for usage. And till 0.42, it was only used in `examples/diffusers/cache_diffusion/pipeline` which has not been updated in 9 months and not used anymore hence removing. Also cherry-picked to `release/0.42.0` branch: https://github.com/NVIDIA/Model-Optimizer/pull/984 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Removed TensorRT/ONNX deployment and inference tooling, related model export/configuration, and runtime helpers from the cache-optimized diffusion examples; removed the cuda-python example dependency. * **Tests** * Removed the example benchmarking script and its associated benchmark test. * **Documentation** * Strengthened dependency-review, security, and PR guidance; updated PR template and contributing documentation. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
62 lines
2.4 KiB
Python
62 lines
2.4 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import subprocess
|
|
import sys
|
|
|
|
import pytest
|
|
import torch
|
|
from _test_utils.examples.models import PIXART_PATH, SXDL_PATH
|
|
from _test_utils.examples.run_command import MODELOPT_ROOT
|
|
from diffusers import DiffusionPipeline, PixArtAlphaPipeline
|
|
|
|
sys.path.append(str(MODELOPT_ROOT / "examples/diffusers/cache_diffusion"))
|
|
from cache_diffusion import cachify
|
|
from cache_diffusion.utils import PIXART_DEFAULT_CONFIG, SDXL_DEFAULT_CONFIG
|
|
|
|
|
|
def test_sdxl_cachify():
|
|
pipe = DiffusionPipeline.from_pretrained(
|
|
SXDL_PATH,
|
|
torch_dtype=torch.float16,
|
|
variant="fp16",
|
|
use_safetensors=True,
|
|
).to("cuda")
|
|
cachify.prepare(pipe, SDXL_DEFAULT_CONFIG)
|
|
|
|
prompt = "A random person with a head that is made of flowers, photo by James C. Leyendecker, \
|
|
Afrofuturism, studio portrait, dynamic pose, national geographic photo, retrofuturism, biomorphicy"
|
|
generator = torch.Generator(device="cuda").manual_seed(2946901)
|
|
pipe(prompt=prompt, generator=generator, num_inference_steps=30).images[0]
|
|
# Clear cuda memory as pytest doesnt clear it between tests
|
|
del pipe
|
|
torch.cuda.empty_cache()
|
|
|
|
|
|
def test_pixart_cachify():
|
|
# Fail test if apex is installed
|
|
if "apex" in subprocess.check_output(["pip", "list"]).decode("utf-8"):
|
|
pytest.xfail("Apex is installed, test is expected to fail")
|
|
|
|
pipe = PixArtAlphaPipeline.from_pretrained(PIXART_PATH, torch_dtype=torch.float16).to("cuda")
|
|
cachify.prepare(pipe, PIXART_DEFAULT_CONFIG)
|
|
|
|
prompt = "a small cactus with a happy face in the Sahara desert"
|
|
generator = torch.Generator(device="cuda").manual_seed(2946901)
|
|
pipe(prompt=prompt, generator=generator, num_inference_steps=30).images[0]
|
|
# Clear cuda memory as pytest doesnt clear it between tests
|
|
del pipe
|
|
torch.cuda.empty_cache()
|