Skip to main content
The UpdateDeploymentConfig class defines the parameters used for updating private serverless deployments. The parameters and their definitions match DeploymentConfig, except for accelerator, which cannot be changed via an update.

​
Parameters

ParameterTypeRequiredDefaultDescription
base_modelstringYesThe base model to deploy. Can be a short name from our models list or Hugging Face model path
cooldown_timeintegerNo3600Time in seconds before scaling down idle replicas. Minimum is 10 minutes (600 seconds)
hf_tokenstringNoHugging Face token for private models
min_replicasintegerNo0Minimum number of replicas
max_replicasintegerNo1Maximum number of replicas
scale_up_thresholdintegerNo1Number of queued requests before scaling up additional replicas
quantizationstringNoQuantization method (none, fp8, bitsandbytes-nf4). Default is based on the model and accelerator.
uses_guaranteed_capacitybooleanNofalseWhether to use guaranteed capacity
max_total_tokensintegerNoMaximum number of tokens per request
max_num_batched_tokensintegerNoMaximum number of tokens that can be batched together. Higher values increase throughput but may cause request preemption
lorax_image_tagstringNoTag for the LoRAX image
request_logging_enabledbooleanNofalseWhether to enable request logging
direct_ingressbooleanNofalseCreates a direct endpoint to the LLM, bypassing the Predibase control plane
preloaded_adaptersarray[string]NoList of adapter IDs to preload on deployment initialization
speculatorstringNoSpeculator to use for the deployment (auto, disabled, or adapter ID of a Turbo or Turbo LoRA)
prefix_cachingbooleanNofalseWhether to enable prefix caching
merge_adapterbooleanNofalseWhether to merge a preloaded adapter with the base model
cache_modelbooleanNofalseIf true, caches the HF weights of the model in a private S3 bucket (see details)
custom_argsarray[string]NoCustom arguments to pass to the LoRAX launcher

​
Example Usage

from predibase import UpdateDeploymentConfig

# Update scaling configuration
pb.deployments.update(
    deployment_ref="my-qwen3-8b",
    config=UpdateDeploymentConfig(
        min_replicas=1,    # Change to always-on (disable scale-to-zero)
        max_replicas=2,    # Allow scaling to 2 replicas for higher load
        cooldown_time=1800 # Change cooldown time
    )
)

# Update batching configuration for higher throughput
pb.deployments.update(
    deployment_ref="my-qwen3-8b",
    config=UpdateDeploymentConfig(
        max_num_batched_tokens=16384  # Increase batch size for better throughput
    )
)

​
Additional Pointers

​
Model caching

Availability: Model caching is exclusively available to VPC customers. Cached models are stored in a private VPC bucket with read access restricted to the VPC customer only. Behavior:
  • Deployments always load model weights fom the S3 cache, if available.
  • The cacheModel parameter controls whether model weights are written to the cache.
Versioning:
  • By default, weights are cached at the latest model revision
  • To cache a specific revision, specify the base_model parameter with the format: model@revision
⌘I