debug Qwen TTS

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>

vllm_omni/model_executor/models/qwen3_tts/configuration_qwen3_tts.py

@@ -504,12 +504,19 @@ class Qwen3TTSConfig(PretrainedConfig):
         self.tts_bos_token_id = tts_bos_token_id
         self.tts_eos_token_id = tts_eos_token_id
 
+        #TODO: remove these dummy values after 
+        self.image_token_id = 0 # dummy image token id
+        self.video_token_id = 0 # dummy video token id
+        self.vision_start_token_id = 0 # dummy vision start token id
+        self.vision_config = PretrainedConfig()  # dummy vision config
+        self.vision_config.spatial_merge_size = 1
+
     def get_text_config(self, **kwargs):
         # vLLM expects text config to expose hidden_size/num_attention_heads.
         # For Qwen3 TTS, the talker config is the text model config.
         config = self.talker_config
-        if hasattr(config, "rope_parameters"):
-            delattr(config, "rope_parameters")
+        # if hasattr(config, "rope_parameters"):
+        #     delattr(config, "rope_parameters")
         return config
 
 

vllm_omni/model_executor/models/qwen3_tts/modeling_qwen3_tts.py

@@ -426,7 +426,20 @@ def mel_spectrogram(
     mel_spec = dynamic_range_compression_torch(mel_spec)
 
     return mel_spec
+def _compute_default_rope_parameters(
+    config,
+    device,
+):
+    base = config.rope_theta
+    partial_rotary_factor = getattr(config, "partial_rotary_factor", 1.0)
+    head_dim = getattr(config, "head_dim", None) or config.hidden_size // config.num_attention_heads
+    dim = int(head_dim * partial_rotary_factor)
 
+    attention_factor = 1.0  # Unused in this type of RoPE
+
+    # Compute the inverse frequencies
+    inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.int64).to(device=device, dtype=torch.float) / dim))
+    return inv_freq, attention_factor
 
 class Qwen3TTSPreTrainedModel(PreTrainedModel):
     config_class = Qwen3TTSConfig
@@ -500,7 +513,9 @@ class Qwen3TTSTalkerRotaryEmbedding(nn.Module):
         self.original_max_seq_len = config.max_position_embeddings
 
         self.config = config
-        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+        self.rope_init_fn: Callable = _compute_default_rope_parameters
+        if self.rope_type != "default":
+            self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
 
         inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
         self.register_buffer("inv_freq", inv_freq, persistent=False)
@@ -536,7 +551,9 @@ class Qwen3TTSRotaryEmbedding(nn.Module):
         self.original_max_seq_len = config.max_position_embeddings
 
         self.config = config
-        self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
+        self.rope_init_fn: Callable = _compute_default_rope_parameters
+        if self.rope_type != "default":
+            self.rope_init_fn = ROPE_INIT_FUNCTIONS[self.rope_type]
 
         inv_freq, self.attention_scaling = self.rope_init_fn(self.config, device)
         self.register_buffer("inv_freq", inv_freq, persistent=False)
@@ -1387,7 +1404,6 @@ class Qwen3TTSTalkerModel(Qwen3TTSTalkerTextPreTrainedModel):
 
     def __init__(self, config):
         super().__init__(config)
-        self.padding_idx = config.pad_token_id
         self.vocab_size = config.vocab_size
         self.layers = nn.ModuleList(
             [Qwen3TTSTalkerDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)]