Operation Enumeration
Function
Specifies the type of the request to stop.
Format
enum class Operation {
STOP = 1,
RELEASE_KV = 2,
};
Enumerated Values
Enumeration |
Description |
|---|---|
STOP |
Type of the request that is stopped by stopInfer. |
RELEASE_KV |
Type of the request that releases the KV cache on the prefill node. |
Parent topic: Structure and Enumeration Description