The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Enable async offloading by default on Nvidia. (#10953)
comfyanonymous9d8a817985bb
diff --git a/comfy/cli_args.py b/comfy/cli_args.pyindex d2b60e347..5f0dfaa10 100644--- a/comfy/cli_args.py+++ b/comfy/cli_args.py@@ -131,7 +131,8 @@ vram_group.add_argument("--cpu", action="store_true", help="To use the CPU for eparser.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.")diff --git a/comfy/model_management.py b/comfy/model_management.pyindex 9c403d580..38c506df5 100644--- a/comfy/model_management.py+++ b/comfy/model_management.py@@ -1013,8 +1013,17 @@ def force_channels_last():STREAMS = {}NUM_STREAMS = 0-if args.async_offload:- NUM_STREAMS = 2+if args.async_offload is not None:+ NUM_STREAMS = args.async_offload+else:+ # Enable by default on Nvidia+ if is_nvidia():+ NUM_STREAMS = 2++if args.disable_async_offload:+ NUM_STREAMS = 0++if NUM_STREAMS > 0:logging.info("Using async weight offloading with {} streams".format(NUM_STREAMS))def current_stream(device):