Merge tag 'v0.9.1' into v0.9.1-ori

tests/models/multimodal/processing/test_internvl.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for InternVL's multimodal preprocessing kwargs."""
 from collections.abc import Mapping
 from typing import Optional

tests/models/multimodal/processing/test_llama4.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for Llama4's multimodal preprocessing kwargs."""
 
 import pytest

tests/models/multimodal/processing/test_llava_next.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import itertools
 from functools import partial

tests/models/multimodal/processing/test_llava_onevision.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import itertools
 from functools import partial

tests/models/multimodal/processing/test_minimax_vl_01.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import pytest
 from PIL import Image

tests/models/multimodal/processing/test_mllama.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for mllama's multimodal preprocessing and profiling."""
 import pytest
 from transformers import MllamaConfig

tests/models/multimodal/processing/test_phi3v.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for phi3v's multimodal preprocessing kwargs."""
 import pytest
 

tests/models/multimodal/processing/test_phi4mm.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for phi4mm's multimodal preprocessing kwargs."""
 import pytest
 

tests/models/multimodal/processing/test_qwen2_vl.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 import pytest
 

tests/models/multimodal/processing/test_smolvlm.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Tests for smolvlm's multimodal preprocessing kwargs."""
 import pytest
 from transformers import SmolVLMConfig

tests/models/quantization/test_aqlm.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 import pytest
 
 from tests.quantization.utils import is_quant_method_supported

tests/models/quantization/test_awq.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 from typing import Optional
 

tests/models/quantization/test_bitblas.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Compare the outputs of a GPTQ model to a bitblas model.
 
 Note: GPTQ and bitblas do not have bitwise correctness.

tests/models/quantization/test_fp8.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 # flake8: noqa
 """Tests fp8 models against ground truth generation

tests/models/quantization/test_gguf.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """
 Tests gguf models against unquantized models generations
 Note: To pass the test, quantization higher than Q4 should be used
@@ -37,7 +38,7 @@ class GGUFTestConfig(NamedTuple):
 LLAMA_CONFIG = GGUFTestConfig(
     original_model="meta-llama/Llama-3.2-1B-Instruct",
     gguf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF",
-    gguf_filename="Llama-3.2-1B-Instruct-IQ4_XS.gguf",
+    gguf_filename="Llama-3.2-1B-Instruct-Q6_K.gguf",
 )
 
 QWEN2_CONFIG = GGUFTestConfig(

tests/models/quantization/test_gptq_bitblas.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Compare the outputs of a GPTQ model to a bitblas model.
 
 Note: GPTQ and bitblas do not have bitwise correctness.

tests/models/quantization/test_gptq_marlin.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Compares the outputs of gptq vs gptq_marlin.
 
 Note: GPTQ and Marlin do not have bitwise correctness.

tests/models/quantization/test_gptq_marlin_24.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 """Compare the outputs of a GPTQ model to a Marlin_24 model.
 
 Note: GPTQ and Marlin_24 do not have bitwise correctness.

tests/models/quantization/test_modelopt.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
 # flake8: noqa
 """Tests Model Optimizer fp8 models against ground truth generation

tests/models/quantization/test_mxfp4.py

 # SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 # flake8: noqa
 """Tests Quark mxfp4 models against ground truth generation
 """