The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Fix int8 mm being skipped on offloaded lora weights. (#14669)
comfyanonymous79c555ce6bfe
diff --git a/comfy/ops.py b/comfy/ops.pyindex 6a5090548..69d32e254 100644--- a/comfy/ops.py+++ b/comfy/ops.py@@ -1216,7 +1216,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_precbias_dtype=input.dtype,offloadable=True,compute_dtype=compute_dtype,- want_requant=want_requant,+ want_requant=True,)weight = weight.to(dtype=input.dtype)else: