mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-10-17 05:29:39 +08:00
Chenjie LuoandClaude Opus 5.5
af07754681
### What does this PR do?
Type of change: Tests (CI speed-up)
The diffusers example lane spends ~29 min in pytest, almost all of it in
~45 example-script subprocesses on tiny models. This PR removes
redundant and avoidable work without dropping coverage:
- **Export HF checkpoints from runs that already happen.** The SDXL
int8/fp8 and Wan 2.2 14B transformer int8/fp8 configs in
`test_export_diffusers_hf_ckpt.py` used exactly the same arguments as
runs in `test_diffusers.py`. Those quantize runs now also pass
`--hf-ckpt-dir` (`hf_export=True`) and check the export, and the four
duplicate export tests are removed (30 → 26 tests in these files).
- **Calibrate from a local prompts file.** `quantize.py` loaded the Hub
prompt datasets on every calibration run. For Wan 2.2 that is all of
`nkp37/OpenVid-1M`, which cost ~30s per run. Tests now pass
`--prompts-file tests/examples/diffusers/calib_prompts.txt`, which also
removes a network dependency.
- **Tiny PixArt for `test_pixart_cachify`.** It downloaded the full-size
`PixArt-XL-2-1024-MS`. It now uses a tiny local PixArt-Alpha pipeline,
with the same tiny config as diffusers' own PixArt tests and built like
the existing tiny Wan 2.2 fixture. `cachify` still wraps both
transformer blocks. `PIXART_PATH` is removed because nothing else uses
it.
- **Cheaper `torch.compile` tests.** `diffusion_trt.py` compiles with
`mode="max-autotune"`. The compile tests now set
`TORCHINDUCTOR_MAX_AUTOTUNE_{GEMM,CONV}_BACKENDS=ATEN`, so Inductor
skips benchmarking Triton GEMM/conv templates. The `--torch-compile`
path still runs.
### Usage
N/A (tests only).
### Testing
I ran these on an RTX PRO 6000 (same GPU as the CI runner) in
`nvcr.io/nvidia/pytorch:26.07-py3`, set up like the CI lane: editable
`.[onnx,hf,dev-test]`, `diffusers==0.39.0`, apex uninstalled. Coverage
was on, the same way CI collects it (`COVERAGE_PROCESS_START`, `--cov`).
- Branch: `pytest tests/examples/diffusers
--ignore=test_diffusers_onnx_trt.py --ignore=fastgen --cov` → **40
passed in 22m37s**. fastgen needs `nemo_automodel`, which I didn't
install; this PR doesn't touch it.
- `main`, same machine: `test_diffusers.py`,
`test_export_diffusers_hf_ckpt.py`, `test_cache_diffusion.py -k "not
pixart"` → **29 passed in 28m21s**. This set is smaller than the branch
run: no sparsity, PixArt or deprecation tests (~1m50s on the branch).
Per-test call times (s), with CI from run 37945140337:
| Test | CI (main) | local main | local branch |
|---|---:|---:|---:|
| `test_wan22_quantization[*]` (7 tests, each) | 66–86 | 79–98 | 49–52 |
| `test_wan22_hf_ckpt_export` (2 tests) | 44 + 46 | 54 + 54 | removed |
| `test_diffusers_hf_ckpt_export[sdxl int8 / fp8]` | 43 + 37 | 32 + 31 |
removed |
| `test_pixart_cachify` | 86 | not run | 1.8 |
| `test_diffusion_trt_torch[sdxl_1.0_torch_compile]` | 132 | 156 | 119 |
| `test_diffusion_trt_torch[flux_schnell_torch_compile]` | 60 | 71 | 57
|
| `test_diffusion_trt_torch[sd3_medium_torch_compile]` | 51 | 58 | 49 |
On the same test set this saves about 7.5 min locally, plus about 84s
for PixArt. Scaled to CI timings, I expect the lane's pytest step to
drop from ~29 min to ~21 min.
The ATen restriction cuts the SDXL compile run from 108s to 63s without
coverage (run on its own). Coverage tracing of Inductor's Python
accounts for most of what remains.
`pre-commit` passes on the changed files.
### Before your PR is "*Ready for review*"
- Is this change backward compatible?: N/A (tests only)
- If you copied code from any other sources or added a new PIP
dependency, did you follow guidance in `CONTRIBUTING.md`: N/A (the tiny
PixArt config values mirror diffusers' own tests, as the existing tiny
Wan 2.2 helper does)
- Did you write any new necessary tests?: N/A
- Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?:
N/A (tests only)
- Did you get Claude approval on this PR?: ❌
### Additional Information
Possible follow-ups not in this PR:
- Run fewer restore subprocesses: one per format instead of all 13,
about 3 min, but it gives up some coverage.
- Run the example scripts in-process like `megatron_example_runner.py`:
about 20s of startup saved per subprocess, but a larger change.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Tests**
* Expanded diffusion-model test coverage for PixArt-Alpha, including
cache behavior and checkpoint exports.
* Added validation that exported checkpoints include configuration and
model-weight files.
* Updated quantization tests to use local calibration prompts and cover
checkpoint export for selected SDXL and Wan 2.2 runs.
* Adjusted compiled test runs to use compatible autotuning settings.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Chenjie Luo <chenjiel@nvidia.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
70 lines
2.8 KiB
Python
70 lines
2.8 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 SDXL_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(
|
|
SDXL_PATH,
|
|
torch_dtype=torch.float16,
|
|
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)
|
|
# 8 steps still exercises the step-modulo cache pattern; this is a runs-without-error smoke test.
|
|
pipe(prompt=prompt, generator=generator, num_inference_steps=8).images[0]
|
|
# Clear cuda memory as pytest doesnt clear it between tests
|
|
del pipe
|
|
torch.cuda.empty_cache()
|
|
|
|
|
|
def test_pixart_cachify(tiny_pixart_path):
|
|
# 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(tiny_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)
|
|
# 8 steps still exercises the step-modulo cache pattern; this is a runs-without-error smoke test.
|
|
pipe(
|
|
prompt=prompt,
|
|
generator=generator,
|
|
num_inference_steps=8,
|
|
use_resolution_binning=False, # the tiny transformer's sample_size has no resolution bin
|
|
).images[0]
|
|
# Clear cuda memory as pytest doesnt clear it between tests
|
|
del pipe
|
|
torch.cuda.empty_cache()
|