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 Gemma4 31B global attention: k_eq_v with 4 KV heads (#17220)
Henry Lee1a82e6d01f39
diff --git a/comfy/text_encoders/gemma4.py b/comfy/text_encoders/gemma4.pyindex bba11b183..bb350802f 100644--- a/comfy/text_encoders/gemma4.py+++ b/comfy/text_encoders/gemma4.py@@ -87,6 +87,8 @@ class Gemma4_31B_Config(Gemma4Config):num_hidden_layers: int = 60num_attention_heads: int = 32num_key_value_heads: int = 16+ num_global_key_value_heads = 4+ attention_k_eq_v = Truevision_bidirectional = Truesliding_attention = [1024, 1024, 1024, 1024, 1024, False]hidden_size_per_layer_input: int = 0