[Refactor][Misc] Remove unused code in diffusion hooks/model_loader (#5270)

Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>

vllm_omni/diffusion/hooks/sequence_parallel.py

@@ -679,87 +679,3 @@ def remove_sequence_parallel(
                 continue
 
             registry.remove_hook(hook_name)
-
-
-def enable_sequence_parallel_for_model(
-    model: nn.Module,
-    config: SequenceParallelConfig | None = None,
-) -> None:
-    """Enable sequence parallelism for a model using its _sp_plan.
-
-    This is a convenience function that reads the model's _sp_plan attribute
-    and applies sequence parallelism automatically.
-
-    Note: This corresponds to `enable_context_parallel_for_model` in diffusers,
-    but uses vLLM-Omni's _sp_plan instead of diffusers' _cp_plan.
-
-    The function performs two main tasks:
-    1. Applies _sp_plan hooks to shard inputs and gather outputs
-    2. Ensures Attention layers are configured for the correct parallel mode
-       (handled automatically by vLLM-Omni's forward_context mechanism)
-
-    Args:
-        model: The model to enable SP for. Must have a _sp_plan attribute.
-        config: Optional config. If None, uses default based on current
-            parallel state.
-
-    Raises:
-        ValueError: If model has no _sp_plan defined.
-
-    Note:
-        vLLM-Omni supports Ulysses + Ring hybrid parallelism:
-        - ulysses_degree > 1: Uses All-to-All communication over Q/K/V heads
-        - ring_degree > 1: Uses Ring attention with K/V passing
-        - Both > 1: Hybrid mode (Ulysses handles head redistribution,
-          Ring handles K/V circulation)
-    """
-    from vllm_omni.diffusion.distributed.parallel_state import (
-        get_ring_parallel_world_size,
-        get_ulysses_parallel_world_size,
-    )
-    from vllm_omni.diffusion.distributed.sp_plan import get_sp_plan_from_model
-
-    plan = get_sp_plan_from_model(model)
-    if plan is None:
-        raise ValueError(
-            f"Model {model.__class__.__name__} has no _sp_plan defined. "
-            f"Define _sp_plan as a class attribute or pass a plan explicitly."
-        )
-
-    if config is None:
-        # Create config from current parallel state
-        ulysses_degree = get_ulysses_parallel_world_size()
-        ring_degree = get_ring_parallel_world_size()
-        config = SequenceParallelConfig(
-            ulysses_degree=ulysses_degree,
-            ring_degree=ring_degree,
-        )
-        if ulysses_degree > 1 and ring_degree > 1:
-            mode = "hybrid"
-        elif ulysses_degree > 1:
-            mode = "ulysses"
-        else:
-            mode = "ring"
-        logger.info(
-            f"Created SP config from parallel state: "
-            f"ulysses_degree={ulysses_degree}, ring_degree={ring_degree}, "
-            f"mode={mode}"
-        )
-
-    apply_sequence_parallel(model, config, plan)
-    logger.info(f"Enabled sequence parallelism for {model.__class__.__name__}")
-
-
-def disable_sequence_parallel_for_model(model: nn.Module) -> None:
-    """Disable sequence parallelism for a model.
-
-    Note: This corresponds to `disable_context_parallel_for_model` in diffusers.
-
-    Args:
-        model: The model to disable SP for.
-    """
-    from vllm_omni.diffusion.distributed.sp_plan import get_sp_plan_from_model
-
-    plan = get_sp_plan_from_model(model)
-    if plan is not None:
-        remove_sequence_parallel(model, plan)