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

Signed-off-by: AnyISalIn <anyisalin@gmail.com>
2024-05-02 00:11:03 +08:00 · 2024-05-02 00:11:03 +08:00 · a88bb9b032
commit a88bb9b032
parent 6f1df80436
1 changed files with 2 additions and 1 deletions
--- a/vllm/config.py
+++ b/vllm/config.py
@ -353,7 +353,8 @@ class CacheConfig:
        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.")