[Bugfix] Reject matryoshka embedding dimensions above hidden size (#46313)

Signed-off-by: EazyReal <8047065+EazyReal@users.noreply.github.com>
Co-authored-by: EazyReal <8047065+EazyReal@users.noreply.github.com>

tests/test_pooling_params.py

@@ -74,6 +74,29 @@ def test_embed_dimensions(model_info: EmbedModelInfo):
         pooling_params.verify(model_config)
 
 
+@dataclass()
+class MockMatryoshkaModelConfig:
+    pooler_config: PoolerConfig
+    is_matryoshka: bool = True
+    matryoshka_dimensions: list[int] | None = None
+    served_model_name: str = "mock-matryoshka-model"
+    embedding_size: int = 32
+
+
+def test_embed_dimensions_matryoshka_without_list_upper_bound():
+    task = "embed"
+    model_config = MockMatryoshkaModelConfig(
+        pooler_config=PoolerConfig(seq_pooling_type="CLS"),
+        matryoshka_dimensions=None,
+        embedding_size=32,
+    )
+
+    PoolingParams(task=task, dimensions=16).verify(model_config)
+
+    with pytest.raises(ValueError):
+        PoolingParams(task=task, dimensions=64).verify(model_config)
+
+
 @pytest.mark.parametrize("task", ["classify"])
 def test_classify(task):
     model_config = MockModelConfig(pooler_config=PoolerConfig(seq_pooling_type="CLS"))

vllm/pooling_params.py

@@ -182,6 +182,11 @@ class PoolingParams(
                         )
                 elif self.dimensions < 1:
                     raise ValueError("Dimensions must be greater than 0")
+                elif self.dimensions > model_config.embedding_size:
+                    raise ValueError(
+                        "Dimensions must be less than or equal to the model's "
+                        f"embedding size ({model_config.embedding_size})"
+                    )
 
         elif self.task in ["classify", "token_classify"]:
             if self.use_activation is None: