first commit
Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled

This commit is contained in:
陈赣
2026-06-05 16:53:03 +08:00
commit 06f1fd69a6
6047 changed files with 1895387 additions and 0 deletions

View File

@@ -0,0 +1,88 @@
# Copyright 2024 The HuggingFace Team. All rights reserved.
#
# 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.
"""
This script is used to get the list of folders under `tests/models` and split the list into `NUM_SLICES` splits.
The main use case is a GitHub Actions workflow file calling this script to get the (nested) list of folders allowing it
to split the list of jobs to run into multiple slices each containing a smaller number of jobs. This way, we can bypass
the maximum of 256 jobs in a matrix.
See the `setup` and `run_models_gpu` jobs defined in the workflow file `.github/workflows/self-scheduled.yml` for more
details.
Usage:
This script is required to be run under `tests` folder of `transformers` root directory.
Assume we are under `transformers` root directory:
```bash
cd tests
python ../utils/split_model_tests.py --num_splits 64
```
"""
import argparse
import ast
import os
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--subdirs",
type=str,
default="",
help="the list of pre-computed model names (directory names under `tests/models`) or directory names under `tests` (except `models`).",
)
parser.add_argument(
"--num_splits",
type=int,
default=1,
help="the number of splits into which the (flat) list of folders will be split.",
)
args = parser.parse_args()
tests = os.getcwd()
model_tests = os.listdir(os.path.join(tests, "models"))
d1 = sorted(filter(os.path.isdir, os.listdir(tests)))
d2 = sorted(filter(os.path.isdir, [f"models/{x}" for x in model_tests]))
d1.remove("models")
d = d2 + d1
if args.subdirs != "":
model_tests = ast.literal_eval(args.subdirs)
# We handle both cases with and without prefix because `push-important-models.yml` returns the list without
# the prefix (i.e. `models`) but `utils/pr_slow_ci_models.py` (called by `self-comment-ci.yml`) returns the
# list with the prefix (`models`) and some directory names under `tests`.
d = []
for x in model_tests:
if os.path.isdir(x):
d.append(x)
if os.path.isdir(f"models/{x}"):
d.append(f"models/{x}")
d = sorted(d)
num_jobs = len(d)
num_jobs_per_splits = num_jobs // args.num_splits
model_splits = []
end = 0
for idx in range(args.num_splits):
start = end
end = start + num_jobs_per_splits + (1 if idx < num_jobs % args.num_splits else 0)
# Only add the slice if it is not an empty list
if len(d[start:end]) > 0:
model_splits.append(d[start:end])
print(model_splits)