Skip to content

fix: move flash imports after maybe_unpack to fix torch import errors #63

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
deanq merged 1 commit into from
Feb 10, 2026
Merged

fix: move flash imports after maybe_unpack to fix torch import errors #63

Show file tree
Hide file tree
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
7 changes: 5 additions & 2 deletions src/lb_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,8 +28,6 @@

from logger import setup_logging
from unpack_volume import maybe_unpack
from runpod_flash.protos.remote_execution import FunctionRequest, FunctionResponse
from remote_executor import RemoteExecutor

# Initialize logging configuration
setup_logging()
Expand All @@ -39,6 +37,11 @@
# This is a no-op for Live Serverless and local development
maybe_unpack()

# Import from bundled /app/runpod_flash (no system package)
# These imports must happen AFTER maybe_unpack() so /app is in sys.path
from runpod_flash.protos.remote_execution import FunctionRequest, FunctionResponse # noqa: E402
from remote_executor import RemoteExecutor # noqa: E402

# Determine mode based on environment variables
is_mothership = os.getenv("FLASH_IS_MOTHERSHIP") == "true"

Expand Down
Loading
Loading