Skip to main content
Create a new autoscale worker group.

​
Signature

​
Parameters

​
template_hash
Optional[str]
Hash of the instance template to use for workers.
​
template_id
Optional[int]
ID of the instance template to use for workers.
​
no_default
bool
default:"False"
Disable the default search query filters when finding offers.
​
launch_args
Optional[str]
Additional CLI arguments passed when launching worker instances.
​
endpoint_name
Optional[str]
Human-readable name for the endpoint this group belongs to.
​
endpoint_id
Optional[int]
ID of the endpoint this worker group belongs to.
​
test_workers
int
default:"3"
Number of test workers to spin up during initial scaling evaluation.
​
gpu_ram
Optional[float]
Minimum GPU RAM in GiB required per worker.
​
search_params
Optional[str]
Query string for filtering available GPU offers (e.g. “gpu_name=RTX_4090 num_gpus=1”).
​
min_load
Optional[float]
Minimum load (requests/sec) below which idle workers are scaled down.
​
target_util
Optional[float]
Target worker utilization ratio (0.0-1.0); workers are added to stay at this level.
​
cold_mult
Optional[float]
Multiplier applied to warm worker count for pre-warming cold workers.
​
cold_workers
Optional[int]
Number of pre-warmed (cold) workers to keep ready.

​
Returns

str, Result from the API call.

​
Example