[ez] Delete more torch version checks <= 2.8 (#33288)

Signed-off-by: angelayi <yiangela7@gmail.com>

vllm/model_executor/layers/quantization/kernels/scaled_mm/pytorch.py

@@ -3,7 +3,6 @@
 
 
 import torch
-from packaging import version
 
 from vllm.config import CompilationMode, get_current_vllm_config
 from vllm.platforms import current_platform
@@ -98,9 +97,6 @@ class RowWiseTorchFP8ScaledMMLinearKernel(TorchFP8ScaledMMLinearKernel):
         if compute_capability is not None and compute_capability < 94:
             return False, "requires compute capability 94 and above."
 
-        if not version.parse(torch.__version__) >= version.parse("2.7"):
-            return False, "requires pytorch version >=2.7."
-
         return True, None
 
     @classmethod