[Feature][Bagel] Add CFG parallel mode (#1578)

Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>

vllm_omni/diffusion/data.py

@@ -77,7 +77,9 @@ class DiffusionParallelConfig:
         assert self.ulysses_degree > 0, "Ulysses degree must be > 0"
         assert self.ring_degree > 0, "Ring degree must be > 0"
         assert self.cfg_parallel_size > 0, "CFG parallel size must be > 0"
-        assert self.cfg_parallel_size in [1, 2], f"CFG parallel size must be 1 or 2, but got {self.cfg_parallel_size}"
+        assert self.cfg_parallel_size in [1, 2, 3], (
+            f"CFG parallel size must be 1, 2, or 3, but got {self.cfg_parallel_size}"
+        )
         assert self.vae_patch_parallel_size > 0, "VAE patch parallel size must be > 0"
         assert self.sequence_parallel_size == self.ulysses_degree * self.ring_degree, (
             "Sequence parallel size must be equal to the product of ulysses degree and ring degree,"