A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 05:45 UTC
[misc] fix typo (#10960)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Dec 6, 2024 at 11:25 UTC
c05cfb67da12f84bd142ba51cca98e59139bea42
1 file changed
+1
-1
vllm/config.py
+1
-1
@@ -2082,7 +2082,7 @@ class KVTransferConfig(BaseModel):
2082
2083
@classmethod
2084
def from_cli(cls, cli_value: str) -> "KVTransferConfig":
2085
- """Parse the CLI value for the compilation config."""
2085
+ """Parse the CLI value for the kv cache transfer config."""
2086
return KVTransferConfig.model_validate_json(cli_value)
2087
2088
def model_post_init(self, __context: Any) -> None: