[pull] master from Comfy-Org:master

CODEOWNERS

@@ -1,5 +1,6 @@
 * @comfyanonymous @kosinkadink @guill @alexisrolland @rattus128 @kijai
 
 /CODEOWNERS @comfyanonymous
+/AGENTS.md @comfyanonymous
 /.ci/ @comfyanonymous
 /.github/ @comfyanonymous

comfy/model_management.py

@@ -473,7 +473,7 @@ def amd_min_version(device=None, min_rdna_version=0):
 
 SUPPORT_FP8_OPS = args.supports_fp8_compute
 
-AMD_RDNA2_AND_OLDER_ARCH = ["gfx1030", "gfx1031", "gfx1010", "gfx1011", "gfx1012", "gfx906", "gfx900", "gfx803"]
+AMD_RDNA2_AND_OLDER_ARCH = ["gfx1030", "gfx1031", "gfx1035", "gfx1010", "gfx1011", "gfx1012", "gfx906", "gfx900", "gfx803"]
 AMD_ENABLE_MIOPEN_ENV = 'COMFYUI_ENABLE_MIOPEN'
 
 try:

comfy/sd.py

@@ -1434,6 +1434,7 @@ class TEModel(Enum):
     GPT_OSS_20B = 33
     QWEN3VL_4B = 34
     QWEN3VL_8B = 35
+    GEMMA_4_12B = 36
 
 
 def detect_te_model(sd):
@@ -1463,6 +1464,9 @@ def detect_te_model(sd):
     if 'model.layers.0.post_feedforward_layernorm.weight' in sd:
         if 'model.layers.59.self_attn.q_norm.weight' in sd:
             return TEModel.GEMMA_4_31B
+        # Gemma4 12B Unified: 48 layers, encoder-free; global layers drop v_proj (attention_k_eq_v).
+        if 'model.layers.47.self_attn.q_norm.weight' in sd and 'model.layers.5.self_attn.v_proj.weight' not in sd:
+            return TEModel.GEMMA_4_12B
         if 'model.layers.41.self_attn.q_norm.weight' in sd and 'model.layers.47.self_attn.q_norm.weight' not in sd:
             return TEModel.GEMMA_4_E4B
         if 'model.layers.34.self_attn.q_norm.weight' in sd and 'model.layers.41.self_attn.q_norm.weight' not in sd:
@@ -1618,10 +1622,11 @@ class EmptyClass:
             clip_target.clip = comfy.text_encoders.sa3.SAT5GemmaModel
             clip_target.tokenizer = comfy.text_encoders.sa3.SAT5GemmaTokenizer
             tokenizer_data["spiece_model"] = clip_data[0].get("spiece_model", None)
-        elif te_model in (TEModel.GEMMA_4_E4B, TEModel.GEMMA_4_E2B, TEModel.GEMMA_4_31B):
+        elif te_model in (TEModel.GEMMA_4_E4B, TEModel.GEMMA_4_E2B, TEModel.GEMMA_4_31B, TEModel.GEMMA_4_12B):
             variant = {TEModel.GEMMA_4_E4B: comfy.text_encoders.gemma4.Gemma4_E4B,
                        TEModel.GEMMA_4_E2B: comfy.text_encoders.gemma4.Gemma4_E2B,
-                       TEModel.GEMMA_4_31B: comfy.text_encoders.gemma4.Gemma4_31B}[te_model]
+                       TEModel.GEMMA_4_31B: comfy.text_encoders.gemma4.Gemma4_31B,
+                       TEModel.GEMMA_4_12B: comfy.text_encoders.gemma4.Gemma4_12B}[te_model]
             clip_target.clip = comfy.text_encoders.gemma4.gemma4_te(**llama_detect(clip_data), model_class=variant)
             clip_target.tokenizer = variant.tokenizer
             tokenizer_data["tokenizer_json"] = clip_data[0].get("tokenizer_json", None)

comfy/text_encoders/llama.py

@@ -876,7 +876,7 @@ def init_kv_cache(self, batch, max_cache_len, device, execution_dtype):
                                     torch.empty([batch, model_config.num_key_value_heads, max_cache_len, model_config.head_dim], device=device, dtype=execution_dtype), 0))
         return past_key_values
 
-    def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0, initial_input_ids=None, position_ids=None, deepstack_embeds=None, visual_pos_masks=None):
+    def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0, top_k=50, top_p=0.9, min_p=0.0, repetition_penalty=1.0, seed=42, stop_tokens=None, initial_tokens=[], execution_dtype=None, min_tokens=0, presence_penalty=0.0, initial_input_ids=None, position_ids=None, deepstack_embeds=None, visual_pos_masks=None, embeds_info=None):
         device = embeds.device
 
         if stop_tokens is None:
@@ -911,7 +911,7 @@ def generate(self, embeds=None, do_sample=True, max_length=256, temperature=1.0,
             if step == 0 and deepstack_embeds is not None:
                 extra["deepstack_embeds"] = deepstack_embeds
                 extra["visual_pos_masks"] = visual_pos_masks
-            x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values, input_ids=current_input_ids, position_ids=position_ids, **extra)
+            x, _, past_key_values = self.model.forward(None, embeds=embeds, attention_mask=None, past_key_values=past_key_values, input_ids=current_input_ids, position_ids=position_ids, **extra, embeds_info=(embeds_info if step == 0 else None))
             logits = self.logits(x)[:, -1]
             next_token = self.sample_token(logits, temperature, top_k, top_p, min_p, repetition_penalty, initial_tokens + generated_token_ids, generator, do_sample=do_sample, presence_penalty=presence_penalty)
             token_id = next_token[0].item()