• Stefy Lanza (nextime / spora )'s avatar
    Fix client disconnection handling in cluster master · d5d30329
    Stefy Lanza (nextime / spora ) authored
    - Made assign_job_to_worker, _transfer_job_files, _transfer_file_via_websocket, enable_process, disable_process, update_process_weight, restart_client_workers, and restart_client_worker async methods
    - Added proper exception handling for websocket send operations
    - When websocket send fails due to broken connection, clients are now properly removed from available workers selection
    - This ensures that disconnected clients are immediately removed from the worker pool and jobs are re-assigned to available workers
    d5d30329
Name
Last commit
Last update
docs Loading commit data...
templates Loading commit data...
vidai Loading commit data...
.gitignore Loading commit data...
AI.PROMPT Loading commit data...
CHANGELOG.md Loading commit data...
Dockerfile.runpod Loading commit data...
LICENSE Loading commit data...
README.md Loading commit data...
TODO.md Loading commit data...
build.bat Loading commit data...
build.sh Loading commit data...
clean.bat Loading commit data...
clean.sh Loading commit data...
create_pod.sh Loading commit data...
image.jpg Loading commit data...
requirements-cuda.txt Loading commit data...
requirements-rocm.txt Loading commit data...
requirements.txt Loading commit data...
setup.bat Loading commit data...
setup.sh Loading commit data...
start.bat Loading commit data...
test_comm.py Loading commit data...
test_runpod.py Loading commit data...
vidai.conf.sample Loading commit data...
vidai.py Loading commit data...
vidai.sh Loading commit data...