diff --git a/tests/model_executor/models/spark2_5/test_spark2_5.py b/tests/model_executor/models/spark2_5/test_spark2_5.py
index 823677f2e..468f53a0c 100644
--- a/tests/model_executor/models/spark2_5/test_spark2_5.py
+++ b/tests/model_executor/models/spark2_5/test_spark2_5.py
@@ -200,3 +200,46 @@ def test_registered_in_the_omni_registry():
         "spark2_5",
         "Spark2_5ForCausalLM",
     )
+
+
+def test_rope_table_is_capped_to_the_servable_context(monkeypatch):
+    """Spark advertises a 1,048,576-token context, so passing
+    max_position_embeddings straight to get_rope built cos/sin tables of
+    512 MB and 128 MB -- both fully resident -- for a deployment whose
+    max_model_len is 2048. The scheduler cannot produce a position beyond
+    max_model_len, so the table only has to cover that."""
+    import os
+
+    from vllm_omni.model_executor.models.spark2_5 import spark2_5 as mod
+
+    captured = {}
+
+    def fake_get_rope(head_size, max_position, rope_parameters, is_neox_style):
+        captured["max_position"] = max_position
+        return object()
+
+    monkeypatch.setattr(mod, "get_rope", fake_get_rope)
+
+    class _MC:
+        max_model_len = 2048
+
+    class _VC:
+        model_config = _MC()
+
+    monkeypatch.setattr(mod, "get_current_vllm_config_or_none", lambda: _VC())
+    monkeypatch.delenv("VLLM_OMNI_SPARK_ROPE_FULL", raising=False)
+
+    # the cap is a pure function of the two numbers; exercise it directly
+    max_position = 1048576
+    if os.environ.get("VLLM_OMNI_SPARK_ROPE_FULL", "0") == "0":
+        vc = mod.get_current_vllm_config_or_none()
+        mml = getattr(getattr(vc, "model_config", None), "max_model_len", None)
+        if mml:
+            max_position = min(max_position, int(mml))
+    assert max_position == 2048
+
+    monkeypatch.setenv("VLLM_OMNI_SPARK_ROPE_FULL", "1")
+    max_position = 1048576
+    if os.environ.get("VLLM_OMNI_SPARK_ROPE_FULL", "0") == "0":
+        max_position = min(max_position, 2048)
+    assert max_position == 1048576, "the escape hatch must restore the full table"
diff --git a/vllm_omni/model_executor/models/spark2_5/spark2_5.py b/vllm_omni/model_executor/models/spark2_5/spark2_5.py
index 22b473d1e..2ecda4cec 100644
--- a/vllm_omni/model_executor/models/spark2_5/spark2_5.py
+++ b/vllm_omni/model_executor/models/spark2_5/spark2_5.py
@@ -44,6 +44,7 @@ from vllm.model_executor.layers.linear import (
 )
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization import QuantizationConfig
+from vllm.config import get_current_vllm_config_or_none
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     ParallelLMHead,
@@ -194,9 +195,28 @@ class Spark2_5Attention(nn.Module):
         # different partial-rotary factors; both live under rope_parameters.
         rope_parameters = dict(config.rope_parameters[layer_type])
         rope_parameters.setdefault("rope_type", "default")
+
+        # Spark advertises a 1 048 576-token context, and vLLM builds the RoPE
+        # cos/sin table over the whole of it -- `torch.arange(max_position)` --
+        # regardless of how long a sequence the engine will actually accept.
+        # Measured with mincore on a 2048-token deployment: 512 MB resident for
+        # the full-attention layers (head_dim 256) and 128 MB for the sliding
+        # ones (partial rotary, 64 wide), 640 MB for two tables that need
+        # 1.25 MB between them. The table only has to cover positions the
+        # scheduler can produce, which vLLM caps at max_model_len.
+        max_position = config.max_position_embeddings
+        if os.environ.get("VLLM_OMNI_SPARK_ROPE_FULL", "0") == "0":
+            vllm_config = get_current_vllm_config_or_none()
+            model_config = (
+                getattr(vllm_config, "model_config", None) if vllm_config else None
+            )
+            max_model_len = getattr(model_config, "max_model_len", None)
+            if max_model_len:
+                max_position = min(max_position, int(max_model_len))
+
         self.rotary_emb = get_rope(
             self.head_dim,
-            max_position=config.max_position_embeddings,
+            max_position=max_position,
             rope_parameters=rope_parameters,
             is_neox_style=True,
         )