Wenbo Ji　嵇文博 8d2e1cf328 [bugfix] Skip streaming IPC queues for standard VideoGenerator (#1902) ...

MultiprocExecutor created two streaming multiprocessing queues for every
generator, but only StreamingVideoGenerator uses them. Each queue uses POSIX
named semaphores in /dev/shm. When a job epilog deleted these files, spawned
workers failed to start. The executor now creates the queues only when
FastVideoArgs.enable_streaming_ipc_queues is set. StreamingVideoGenerator sets
it on a copy of its arguments in queue mode. Standard generation creates no
streaming semaphores.

2026-10-07 15:33:11 -07:00

..

__init__.py

[bugfix] use in-process executor for num_gpus=1 (#1755) (#1879)

2026-10-07 02:18:23 -07:00

executor.py

[feat] Add external-launcher executor for multi-node inference (#1746)

2026-10-07 04:46:26 -07:00

external_launcher_executor.py

[feat] Add external-launcher executor for multi-node inference (#1746)

2026-10-07 04:46:26 -07:00

gpu_worker.py

[bugfix] Return individual images for batched image API requests (#1917)

2026-10-07 15:06:02 -07:00

multiproc_executor.py

[bugfix] Skip streaming IPC queues for standard VideoGenerator (#1902)

2026-10-07 15:33:11 -07:00

ray_distributed_executor.py

[bugfix] Fix the CUDA device of Ray workers on multi-GPU nodes (#1932)

2026-10-07 15:00:23 -07:00

ray_env.py

[misc] Move environment var reads into env registry and rename unprefixed variables (#1897)

2026-09-29 14:36:16 -07:00

ray_utils.py

[bugfix] Fix the CUDA device of Ray workers on multi-GPU nodes (#1932)

2026-10-07 15:00:23 -07:00

uniproc_executor.py

[bugfix] use in-process executor for num_gpus=1 (#1755) (#1879)

2026-10-07 02:18:23 -07:00

worker_base.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00