[Diffusion] Prefer host-cache registration when pinned

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/diffusion/model_loader/diffusers_loader.py

@@ -441,15 +441,13 @@ class DiffusersPipelineLoader:
                 _dp_size = int(getattr(self.parallel_config, "data_parallel_size", 1))
                 _sp_size = int(getattr(self.parallel_config, "sequence_parallel_size", 1))
                 _dlo_group_size = _dp_size if _dp_size > 1 else _sp_size
-                _prefer_registered_host_weight_cache = (
-                    _dist_offload
-                    and not _use_ag
-                    and float(getattr(self.od_config, "dlo_host_weight_cache_pin_limit_gib", 0.0)) > 0
+                _select_host_weight_cache = (
+                    _dist_offload and not _use_ag and bool(getattr(self.od_config, "dlo_use_host_weight_cache", False))
                 )
 
                 plan_result = None
                 weight_sources = self._get_weight_sources(model)
-                if _dist_offload and not _prefer_registered_host_weight_cache:
+                if _dist_offload and not _select_host_weight_cache:
                     modules = ModuleDiscovery.discover(model)
                     plan_result = build_checkpoint_mmap_plan(
                         model,
@@ -461,14 +459,14 @@ class DiffusersPipelineLoader:
                         online_quantization=_has_online_quant,
                     )
                     self.host_weight_plan = plan_result.plan
-                elif _prefer_registered_host_weight_cache:
+                elif _select_host_weight_cache:
                     # Direct checkpoint bindings can carry deferred transforms
                     # (for example grouped-QKV reordering), so registering the
                     # raw checkpoint mapping would not make every recurrent H2D
                     # source directly copyable. Materialize once, apply every
                     # post-load mutation, then publish/register the final layout.
                     logger.info(
-                        "DLO host weight cache registration requested; using the ordinary loader "
+                        "DLO host weight cache selected; using the ordinary loader "
                         "once to publish a transform-complete final mmap layout"
                     )
 
@@ -550,10 +548,7 @@ class DiffusersPipelineLoader:
             return
         if getattr(self.od_config, "dlo_use_allgather", True):
             return
-        if not (
-            getattr(self.od_config, "dlo_use_host_weight_cache", False)
-            or float(getattr(self.od_config, "dlo_host_weight_cache_pin_limit_gib", 0.0)) > 0
-        ):
+        if not getattr(self.od_config, "dlo_use_host_weight_cache", False):
             logger.info(
                 "DLO host weight cache not selected; retaining ordinary host tensors after checkpoint mmap fallback"
             )