[Perf] Support request-level batching for Wan2.2 pipelines (#5676)

Signed-off-by: nagisa-kun <1434936049@qq.com>
Signed-off-by: nagisa <1434936049@qq.com>

vllm_omni/engine/stage_engine_startup.py

@@ -1558,6 +1558,7 @@ def launch_diffusion_stage_replica(
     from vllm_omni.diffusion.stage_diffusion_client import StageDiffusionClient
 
     od_config = build_diffusion_config(model, stage_config, metadata)
+    od_config.max_num_seqs = batch_size
     parallel_config = getattr(od_config, "parallel_config", None)
     world_size = getattr(parallel_config, "world_size", 1)
     try:

vllm_omni/engine/stage_init_utils.py

@@ -1441,6 +1441,7 @@ def initialize_diffusion_stage(
     from vllm_omni.diffusion.stage_diffusion_client import create_diffusion_client
 
     od_config = build_diffusion_config(model, stage_cfg, metadata)
+    od_config.max_num_seqs = batch_size
     return create_diffusion_client(model, od_config, metadata, stage_init_timeout, batch_size, use_inline)