diff --git a/vllm/config/cache.py b/vllm/config/cache.py index 04b1e7bf2ac1d..c01643fbff25f 100644 --- a/vllm/config/cache.py +++ b/vllm/config/cache.py @@ -19,7 +19,7 @@ else: logger = init_logger(__name__) -BlockSize = Literal[1, 8, 16, 32, 64, 128] +BlockSize = Literal[1, 8, 16, 32, 64, 128, 256] CacheDType = Literal["auto", "bfloat16", "fp8", "fp8_e4m3", "fp8_e5m2", "fp8_inc"] MambaDType = Literal["auto", "float32"] PrefixCachingHashAlgo = Literal["sha256", "sha256_cbor"]