feat(minimax-h3): enable 2x RTX 4090/5090 with DLO (#5764)

Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>

vllm_omni/diffusion/offloader/offload_plan.py

@@ -35,10 +35,21 @@ class OffloadPlan:
             for large non-DiT submodules within a DiT that should be
             independently offloaded with their own hooks.
             e.g. ``{"context_encoder": "layers"}``
+        resident_dit_paths: DiT paths whose leading blocks may be kept on the
+            device when ``dlo_resident_layers`` is nonzero. Keeping this
+            model-declared avoids applying a consumer-GPU tuning knob to
+            auxiliary or dual DiTs unintentionally.
+        encoder_block_attrs: Maps encoder paths to rank-local block-list paths.
+            These blocks are streamed with ordinary layerwise hooks, never
+            with the DiT AllGather group.
     """
 
+    on_demand_component_paths: frozenset[str] = field(default_factory=frozenset)
+
     block_attrs: dict[str, tuple[str, ...]] = field(default_factory=dict)
     offload_submodules: dict[str, str] = field(default_factory=dict)
+    resident_dit_paths: frozenset[str] = field(default_factory=frozenset)
+    encoder_block_attrs: dict[str, tuple[str, ...]] = field(default_factory=dict)
 
 
 def get_offload_plan(pipeline: nn.Module) -> OffloadPlan | None:
@@ -58,4 +69,6 @@ def supports_mmap_loading(pipeline: nn.Module) -> bool:
     (to decide whether to call ``_load_weights_via_mmap``), ensuring both
     paths use the same gate condition.
     """
-    return any(callable(getattr(type(m), "_remap_ckpt_key", None)) for m in pipeline.modules())
+    return bool(getattr(pipeline, "_supports_mmap_loading", True)) and any(
+        callable(getattr(type(m), "_remap_ckpt_key", None)) for m in pipeline.modules()
+    )