API for Querying the Task Status Between Prefill and Decode Nodes
Function
Queries the status of tasks between prefill and decode nodes.
This API does not need to be called by users. It is a communication API between the Coordinator and Controller.
Format
Operation type: POST
URL: https://{ip}:{port}/v1/instances/query_tasks
- Preferably set {ip} to {manage_ip} in Starting Coordinator. If the parameter is not configured, set {ip} to the value of the manage_ip parameter in the ms_coordinator.json configuration file.
- Preferably set {port} to {manage_port} in Starting Coordinator. If the parameter is not configured, set {port} to the value of the manage_port parameter in the ms_coordinator.json configuration file.
Request Parameters
Parameter |
Type |
Description |
|---|---|---|
p_id |
uint64_t |
Mandatory. Prefill node ID. |
d_id |
uint64_t |
Mandatory. Decode node ID. |
Usage Example
Request example:
POST https://{ip}:{port}/v1/instances/query_tasks
Request body:
{
"p_id": 0,
"d_id": 1
}
Response example:
- There is no task between PDs.
{ "is_end": true } - There are tasks between PDs.
{ "is_end": false }
Output Description
Parameter |
Type |
Description |
|---|---|---|
is_end |
Bool |
Whether the task between PDs is complete. |
Parent topic: Intra-cluster Communication APIs