FRfriendli
Dedicated.Endpoint

Update endpoint spec

Update the specification of a specific endpoint

put/dedicated/beta/endpoint/{endpoint_id}

Request

Path parameters

endpoint_idstring required

The ID of the endpoint

Headers

X-Friendli-Teamstring nullable

ID of team to run requests as (optional parameter).

Request body

namestring nullable

The name of the endpoint.

hfModelRepostring nullable

HF ID of the model.

hfModelRepoRevisionstring nullable

HF commit hash of the model.

newVersionCommentstring nullable

Comment for the new version.

instanceOptionIdstring nullable

The ID of the instance option.

Available options:

  • 1x NVIDIA A100 80GB: ShbPuOs4tfGb
  • 2x NVIDIA A100 80GB: mrAHuYt7T40o
  • 4x NVIDIA A100 80GB: JkNob0NMdoF3
  • 8x NVIDIA A100 80GB: sYH4kHmAcA5P
  • 1x NVIDIA H100: TwD5AqnBSVN0
  • 2x NVIDIA H100: zfTutSiLn0Hq
  • 4x NVIDIA H100: lfkRz5G48REc
  • 8x NVIDIA H100: GUA4qYFmsYz8
  • 1x NVIDIA H200: LnK1wTaKc7WO
  • 2x NVIDIA H200: Tu6GjBnfHPe4
  • 4x NVIDIA H200: OhTzYtZuomzI
  • 8x NVIDIA H200: ahBzWtOuomsI
  • 1x NVIDIA B200: 8GiQTLKfJNOr
  • 2x NVIDIA B200: brTZGIuYgVrs
  • 4x NVIDIA B200: AFoZMFXZnAdD
  • 8x NVIDIA B200: drbc6G9FxJWZ

Response

Successfully updated the endpoint specification.

namestring required

The name of the endpoint.

gpuTypestring required

The type of GPU to use for the endpoint.

numGpuinteger required

The number of GPUs to use per replica.

instanceIdstring nullable

The ID of the instance.

projectIdstring required

The ID of the project that owns the endpoint.

creatorIdstring required

The ID of the user who created the endpoint.

teamIdstring required

The ID of the team that owns the endpoint.

autoscalingMininteger required

The minimum number of replicas to maintain.

autoscalingMaxinteger required

The maximum number of replicas allowed.

autoscalingCooldowninteger required

The cooldown period in seconds between scaling operations.

maxBatchSizeinteger required

The maximum batch size for inference requests.

maxInputLengthinteger nullable

The maximum allowed input length.

tokenizerSkipSpecialTokensboolean required

Whether to skip special tokens in tokenizer output.

tokenizerAddSpecialTokensboolean required

Whether to add special tokens in tokenizer input.

currReplicaCntinteger nullable

The current number of replicas.

desiredReplicaCntinteger nullable

The desired number of replicas.

updatedReplicaCntinteger nullable

The updated number of replicas.

Changes

No recorded changes to this operation across all 1 revision of this API.