[CI/Build] upgrade compressed-tensors to 0.12.2 to address LGPLv3 (vllm-project#26501)

Signed-off-by: Sangyeon Cho <josang1204@gmail.com>
Signed-off-by: xuebwang-amd <xuebwang@amd.com>

Author: csy1204

requirements/common.txt

@@ -38,7 +38,7 @@ pyyaml
 six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12
 setuptools>=77.0.3,<80; python_version > '3.11' # Setuptools is used by triton, we need to ensure a modern version is installed for 3.12+ so that it does not try to import distutils, which was removed in 3.12
 einops # Required for Qwen2-VL.
-compressed-tensors == 0.11.0 # required for compressed-tensors
+compressed-tensors == 0.12.2 # required for compressed-tensors
 depyf==0.19.0 # required for profiling and debugging with compilation config
 cloudpickle # allows pickling lambda functions in model_executor/models/registry.py
 watchfiles # required for http server to monitor the updates of TLS files

vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py

@@ -310,7 +310,7 @@ def _is_fp4a4_nvfp4(
         )
         is_float_type = (
             weight_quant.type == QuantizationType.FLOAT
-            and input_quant.type == QuantizationType.FLOAT.value
+            and input_quant.type == QuantizationType.FLOAT
         )
         is_4_bits = weight_quant.num_bits == 4 and input_quant.num_bits == 4
 

vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py

@@ -143,7 +143,7 @@ def get_moe_method(
             # Prefer to use the MarlinMoE kernel when it is supported.
             if not check_moe_marlin_supports_layer(layer, group_size):
                 if (
-                    weight_quant.strategy in QuantizationStrategy.GROUP
+                    weight_quant.strategy == QuantizationStrategy.GROUP
                     and weight_quant.actorder
                     in (ActivationOrdering.GROUP, ActivationOrdering.DYNAMIC)
                 ):