[Rebase] Rebase to vllm v0.16.0 (#1357)

Signed-off-by: Taichang Zhou <tzhouam@connect.ust.hk>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: ZJY0516 <zhu.jiangyun@foxmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

vllm_omni/diffusion/diffusion_engine.py

@@ -331,6 +331,10 @@ class DiffusionEngine:
                 height=height,
                 width=width,
                 num_inference_steps=num_inference_steps,
+                # Keep warmup path minimal and robust across text encoders.
+                # Some models may fail when warmup implicitly triggers
+                # classifier-free guidance with an empty negative prompt.
+                guidance_scale=0.0,
                 num_outputs_per_prompt=1,
             ),
         )