Skip to content

Handle import path change for vllm lora #376

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
danielhanchen merged 3 commits into from
Dec 9, 2025
Merged

Handle import path change for vllm lora #376

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
25afc44
Handle import path change for vllm lora
Datta0 Dec 9, 2025
00a8d68
Better handle sleep and wakeup
Datta0 Dec 9, 2025
a0f2852
Revert "Better handle sleep and wakeup"
Datta0 Dec 9, 2025
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
10 changes: 8 additions & 2 deletions unsloth_zoo/vllm_lora_worker_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,14 @@ def __init__(self, device):

from vllm.config import LoRAConfig
from vllm.logger import init_logger
from vllm.lora.models import (LoRAModel, LoRAModelManager,
LRUCacheLoRAModelManager, create_lora_manager)
try:
from vllm.lora.models import (LoRAModel, LoRAModelManager,
LRUCacheLoRAModelManager, create_lora_manager)
except ImportError:
# Newer vLLM version moved/split lora methods
# https://github.com/vllm-project/vllm/pull/30253
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Dec 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The URL in this comment is broken and leads to a 404 error, which makes it difficult for future developers to understand the context for this change. The correct pull request appears to be #4701. Please update the link to improve code maintainability.

Suggested change
# https://github.com/vllm-project/vllm/pull/30253
# https://github.com/vllm-project/vllm/pull/4701

from vllm.lora.lora_model import LoRAModel
from vllm.lora.model_manager import LoRAModelManager, LRUCacheLoRAModelManager, create_lora_manager
from vllm.lora.peft_helper import PEFTHelper
from vllm.lora.request import LoRARequest
from vllm.lora.utils import get_adapter_absolute_path
Expand Down