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 offload by default for AMD. (#11534)
comfyanonymous2943093a5310
diff --git a/comfy/model_management.py b/comfy/model_management.pyindex 1889ab0ac..e5554e225 100644--- a/comfy/model_management.py+++ b/comfy/model_management.py@@ -1019,8 +1019,8 @@ NUM_STREAMS = 0if args.async_offload is not None:NUM_STREAMS = args.async_offloadelse:- # Enable by default on Nvidia- if is_nvidia():+ # Enable by default on Nvidia and AMD+ if is_nvidia() or is_amd():NUM_STREAMS = 2if args.disable_async_offload: