[Diffusion] Register HWR mmap for direct DLO H2D (#6591)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>

tests/entrypoints/test_async_omni_diffusion_config.py

@@ -378,6 +378,8 @@ def test_serve_cli_forwards_hwr_policy_for_no_allgather_dlo():
             "preferred",
             "--host-weight-runtime-root",
             "/var/cache/vllm-omni/hwr",
+            "--dlo-host-registration-limit-gib",
+            "80",
         ]
     )
 
@@ -387,8 +389,10 @@ def test_serve_cli_forwards_hwr_policy_for_no_allgather_dlo():
 
     assert explicit_kwargs["host_weight_runtime_mode"] == "preferred"
     assert explicit_kwargs["host_weight_runtime_root"] == "/var/cache/vllm-omni/hwr"
+    assert explicit_kwargs["dlo_host_registration_limit_gib"] == 80
     assert engine_args["host_weight_runtime_mode"] == "preferred"
     assert engine_args["host_weight_runtime_root"] == "/var/cache/vllm-omni/hwr"
+    assert engine_args["dlo_host_registration_limit_gib"] == 80
 
 
 def test_serve_cli_accepts_diffusion_compile_controls():