Skip to content

[Misc] Log time consumption on weight downloading #12926

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Feb 8, 2025
Merged

[Misc] Log time consumption on weight downloading #12926

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 10 additions & 1 deletion vllm/model_executor/model_loader/weight_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@
import json
import os
import tempfile
import time
from collections import defaultdict
from typing import Any, Callable, Dict, Generator, List, Optional, Tuple, Union

Expand All @@ -14,7 +15,8 @@
import huggingface_hub.constants
import numpy as np
import torch
from huggingface_hub import HfFileSystem, hf_hub_download, snapshot_download
from huggingface_hub import (HfFileSystem, hf_hub_download, scan_cache_dir,
snapshot_download)
from safetensors.torch import load_file, safe_open, save_file
from tqdm.auto import tqdm

Expand Down Expand Up @@ -253,6 +255,8 @@ def download_weights_from_hf(
# Use file lock to prevent multiple processes from
# downloading the same model weights at the same time.
with get_lock(model_name_or_path, cache_dir):
start_size = scan_cache_dir().size_on_disk
start_time = time.perf_counter()
hf_folder = snapshot_download(
model_name_or_path,
allow_patterns=allow_patterns,
Expand All @@ -262,6 +266,11 @@ def download_weights_from_hf(
revision=revision,
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
)
end_time = time.perf_counter()
end_size = scan_cache_dir().size_on_disk
if end_size != start_size:
logger.info("Time took to download weights for %s: %.6f seconds",
model_name_or_path, end_time - start_time)
return hf_folder


Expand Down