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/entrypoints/cli/serve.py

@@ -646,15 +646,25 @@ class OmniServeCommand(CLISubcommand):
             action="store_true",
             default=True,
             help="Use shard + AllGather for weight reconstruction (default: True). "
-            "When disabled (--dlo-no-use-allgather), each rank loads full weights "
-            "via H2D only — no sharding, no AllGather, no concurrent request "
-            "requirement, but N× CPU memory.",
+            "When disabled (--dlo-no-use-allgather), each rank streams the "
+            "standard loader's rank-local tensors via H2D only — no additional "
+            "DP sharding, no AllGather, and no concurrent-request requirement.",
         )
         omni_config_group.add_argument(
             "--dlo-no-use-allgather",
             dest="dlo_use_allgather",
             action="store_false",
-            help="Disable AllGather: each rank loads full weights independently.",
+            help=(
+                "Disable AllGather and stream standard-loader rank-local weights "
+                "independently (including existing TP shards)."
+            ),
+        )
+        omni_config_group.add_argument(
+            "--dlo-resident-layers",
+            type=int,
+            default=0,
+            help="Keep this many leading main-DiT blocks resident on the device "
+            "while distributed layerwise offload streams the remaining blocks.",
         )
         # Video model parameters (e.g., Wan2.2) - engine-level
         omni_config_group.add_argument(