Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Make Ernie use comfy kitchen rms rope (#15055)

comfyanonymous0cb84e7e6e0b
diff --git a/comfy/ldm/ernie/model.py b/comfy/ldm/ernie/model.py
index f158ca1d2..88a3775d0 100644
--- a/comfy/ldm/ernie/model.py
+++ b/comfy/ldm/ernie/model.py
@@ -5,6 +5,7 @@ import torch.nn.functional as F
from comfy.ldm.modules.attention import optimized_attention
import comfy.model_management
+import comfy.ops
import comfy.quant_ops
def rope(pos: torch.Tensor, dim: int, theta: int) -> torch.Tensor:
@@ -111,11 +112,17 @@ class ErnieImageAttention(nn.Module):
query = q_flat.view(B, S, self.heads, self.head_dim)
key = k_flat.view(B, S, self.heads, self.head_dim)
- query = self.norm_q(query)
- key = self.norm_k(key)
-
- if image_rotary_emb is not None:
- query, key = comfy.quant_ops.ck.apply_rope_split_half(query, key, image_rotary_emb)
+ if image_rotary_emb is not None and not comfy.model_management.in_training:
+ q_scale, _, q_offload_stream = comfy.ops.cast_bias_weight(self.norm_q, query, offloadable=True)
+ k_scale, _, k_offload_stream = comfy.ops.cast_bias_weight(self.norm_k, key, offloadable=True)
+ query, key = comfy.quant_ops.ck.rms_rope_split_half(query, key, image_rotary_emb, q_scale, k_scale, self.norm_q.eps)
+ comfy.ops.uncast_bias_weight(self.norm_q, q_scale, None, q_offload_stream)
+ comfy.ops.uncast_bias_weight(self.norm_k, k_scale, None, k_offload_stream)
+ else:
+ query = self.norm_q(query)
+ key = self.norm_k(key)
+ if image_rotary_emb is not None:
+ query, key = comfy.quant_ops.ck.apply_rope_split_half(query, key, image_rotary_emb)
q_flat = query.reshape(B, S, -1)
k_flat = key.reshape(B, S, -1)