[Bugfix] Fix the fp8 kv_cache check error that occurs when failing to obtain the CUDA version. (vllm-project#4173)

Signed-off-by: AnyISalIn <anyisalin@gmail.com>

Author: AnyISalIn

vllm/config.py

@@ -385,7 +385,8 @@ def _verify_cache_dtype(self) -> None:
         elif self.cache_dtype == "fp8":
             if not is_hip():
                 nvcc_cuda_version = get_nvcc_cuda_version()
-                if nvcc_cuda_version < Version("11.8"):
+                if nvcc_cuda_version is not None \
+                        and nvcc_cuda_version < Version("11.8"):
                     raise ValueError(
                         "FP8 is not supported when cuda version is"
                         "lower than 11.8.")