[V1] Add V1 support of Qwen2-VL (#12128)

Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: imkero <kerorek@outlook.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/qwen2.py

@@ -256,7 +256,15 @@ class Qwen2DecoderLayer(nn.Module):
         return hidden_states, residual
 
 
-@support_torch_compile
+@support_torch_compile(
+    dynamic_arg_dims={
+        "input_ids": 0,
+        # positions is of shape (3, seq_len) if mrope is enabled for qwen2-vl,
+        # otherwise (seq_len, ).
+        "positions": -1,
+        "intermediate_tensors": 0,
+        "inputs_embeds": 0,
+    })
 class Qwen2Model(nn.Module):
 
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):