Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Speedup modular conversion w/ multiproc #36073

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 9 additions & 4 deletions utils/check_modular_conversion.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,9 @@
import difflib
import glob
import logging
import multiprocessing
from io import StringIO
from multiprocessing import Pool

from create_dependency_mapping import find_priority_list

Expand Down Expand Up @@ -52,7 +54,8 @@ def process_file(modular_file_path, generated_modeling_content, file_type="model
return 0


def compare_files(modular_file_path, fix_and_overwrite=False):
def compare_files(args):
modular_file_path, fix_and_overwrite = args
# Generate the expected modeling content
generated_modeling_content = convert_modular_file(modular_file_path)
diff = 0
Expand All @@ -72,9 +75,11 @@ def compare_files(modular_file_path, fix_and_overwrite=False):
args = parser.parse_args()
if args.files == ["all"]:
args.files = glob.glob("src/transformers/models/**/modular_*.py", recursive=True)
non_matching_files = 0
for modular_file_path in find_priority_list(args.files):
non_matching_files += compare_files(modular_file_path, args.fix_and_overwrite)

num_cores = max(1, multiprocessing.cpu_count() - 1) # Use all cores except one to avoid overloading the system
with Pool(num_cores) as pool:
files_with_args = [(f, args.fix_and_overwrite) for f in find_priority_list(args.files)]
non_matching_files = sum(pool.map(compare_files, files_with_args))

if non_matching_files and not args.fix_and_overwrite:
raise ValueError("Some diff and their modeling code did not match.")