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 OOM regression in _apply() for quantized models during inference (#13372)
Jun Yamog1de83f91c34a
diff --git a/comfy/ops.py b/comfy/ops.pyindex b5cd1d47e..7a9b4b84c 100644--- a/comfy/ops.py+++ b/comfy/ops.py@@ -1151,7 +1151,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_precif param is None:continuep = fn(param)- if p.is_inference():+ if (not torch.is_inference_mode_enabled()) and p.is_inference():p = p.clone()self.register_parameter(key, torch.nn.Parameter(p, requires_grad=False))for key, buf in self._buffers.items():