[Bugfix] Fix the fp8 kv_cache check error that occurs when failing to…

… obtain the CUDA version. (vllm-project#4173) Signed-off-by: AnyISalIn <[email protected]>
opendatahub-io · May 7, 2024 · 3e2c2dc · 3e2c2dc
1 parent e6f4756
commit 3e2c2dc
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/vllm/config.py b/vllm/config.py
@@ -353,7 +353,8 @@ 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.")