diff --git a/docs/design/feature/offloader/distributed_layerwise_offload.md b/docs/design/feature/offloader/distributed_layerwise_offload.md
index 48c72c95a..d7c47e22a 100644
--- a/docs/design/feature/offloader/distributed_layerwise_offload.md
+++ b/docs/design/feature/offloader/distributed_layerwise_offload.md
@@ -143,6 +143,35 @@ is no-AllGather-only, and it selects the backend transfer protocol. This is
 coordination through typed configuration and `HostWeightPlan`, not through
 model-specific global state.
 
+### Runtime host-layout identity (v1)
+
+Host weight cache v1 identifies the loader-produced host representation, not
+the topology used later to move weights to devices. These are separate
+contracts:
+
+- `RuntimeHostLayout` describes tensor ownership and representation after the
+  ordinary loader has applied its parallel-aware transforms. This is the
+  layout stored in the host weight cache.
+- `DLOTransferLayout` describes whether each worker copies its local weights
+  directly or participates in the existing DLO AllGather protocol. It is not
+  part of the host weight cache in v1; AllGather continues to use its existing
+  process-owned host shards.
+
+The v1 physical-sharing invariant is one cache entry per TP coordinate,
+shared by equivalent DP and SP consumers on the same node. The identity
+therefore includes TP world size and TP rank, because different TP coordinates
+own different tensors. It excludes DP world size/rank and SP rank, because
+those dimensions do not change the final tensor ownership supported by v1.
+SP world size and implementation details remain conservative compatibility
+guards until equivalent layouts across those configurations are proven.
+
+PP, HSDP/DTensor, expert parallelism, and CFG parallelism are rejected rather
+than assigned speculative cache identities. Supporting one of these layouts
+requires first defining its loader-produced ownership, representation, and
+sharing domain; it does not follow automatically from supporting its runtime
+collectives. Consequently, this phase implements a TP-coordinate runtime host
+layout, not a general parallel-layout cache.
+
 ### Shared startup and lifecycle
 
 The shared control path selects host backing and transfers its ownership to
diff --git a/tests/diffusion/model_loader/test_host_weight_cache.py b/tests/diffusion/model_loader/test_host_weight_cache.py
index 634299dcf..74f34e1fb 100644
--- a/tests/diffusion/model_loader/test_host_weight_cache.py
+++ b/tests/diffusion/model_loader/test_host_weight_cache.py
@@ -162,6 +162,14 @@ def test_expert_parallel_ownership_fails_closed(tmp_path):
     assert list(tmp_path.rglob("*.safetensors")) == []
 
 
+def test_pipeline_parallel_ownership_fails_closed(tmp_path):
+    result = _build(_Pipeline(), tmp_path, pipeline_parallel_size=2)
+
+    assert result.plan is None
+    assert result.fallback_code == "unsupported_pp"
+    assert list(tmp_path.rglob("*.safetensors")) == []
+
+
 def test_corrupt_published_entry_is_rebuilt_under_the_key_lock(tmp_path):
     first = _build(_Pipeline(), tmp_path)
     assert first.plan is not None
diff --git a/vllm_omni/diffusion/model_loader/host_weight_cache.py b/vllm_omni/diffusion/model_loader/host_weight_cache.py
index 1b6d4be78..e0e4ec2ab 100644
--- a/vllm_omni/diffusion/model_loader/host_weight_cache.py
+++ b/vllm_omni/diffusion/model_loader/host_weight_cache.py
@@ -480,6 +480,9 @@ def build_host_weight_cache_plan(
     try:
         records = _collect_runtime_tensors(pipeline, dit_modules)
         content_digest = runtime_content_digest(records)
+        # The cache stores loader-produced ownership: TP coordinates differ,
+        # while equivalent DP replicas and SP ranks may share one entry. The
+        # conservative SP guard prevents reuse across unproven implementations.
         layout_identity = {
             "schema_version": HOST_WEIGHT_CACHE_SCHEMA_VERSION,
             "model": (canonicalize_existing_local_path(model_identity) if model_identity is not None else None),