andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Enable async offloading by default on Nvidia. (#10953)

Browse Source 
Add --disable-async-offload to disable it.

If this causes OOMs that go away when you --disable-async-offload please
report it.
This commit is contained in:
comfyanonymous
2025-11-27 14:46:12 -08:00
committed by GitHub
parent b59750a86a
commit 9d8a817985
2 changed files with 13 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
comfy/cli_args.py
View File

@@ -131,7 +131,8 @@ vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for e
parser.add_argument("--reserve-vram", type=float, default=None, help="Set the amount of vram in GB you want to reserve for use by your OS/other software. By default some amount is reserved depending on your OS.")
parser.add_argument("--async-offload", action="store_true", help="Use async weight offloading.")
parser.add_argument("--async-offload", nargs='?', const=2, type=int, default=None, metavar="NUM_STREAMS", help="Use async weight offloading. An optional argument controls the amount of offload streams. Default is 2. Enabled by default on Nvidia.")
parser.add_argument("--disable-async-offload", action="store_true", help="Disable async weight offloading.")
parser.add_argument("--force-non-blocking", action="store_true", help="Force ComfyUI to use non-blocking operations for all applicable tensors. This may improve performance on some non-Nvidia systems but can cause issues with some workflows.")