RL

Weights sync

Changed on

Submits a weights-sync operation that makes the session's current trained parameters available for sampling. Call this after optim-step when you want subsequent samples to use the updated policy.

post/v1/rl/training-sessions/{session_id}/operations/weights-sync

Request

  • Base URL
    https://api.together.ai
  • URL
    https://api.together.ai/v1/rl/training-sessions/{session_id}/operations/weights-sync
  • Auth
    HTTP bearer

Path parameters

session_idstring required

Training session ID

Headers

Idempotency-Keystring required

Required key that makes retries return the original operation; use a new key for changed request bodies.

Request body

weight_sync_type'WEIGHT_SYNC_TYPE_SYNCHRONOUS' | 'WEIGHT_SYNC_TYPE_BACKGROUND_PUBLISH' | 'WEIGHT_SYNC_TYPE_PIPELINE' required

How updated policy parameters are made available for sampling. SYNCHRONOUS waits for the policy update before returning; BACKGROUND_PUBLISH returns after scheduling the update; PIPELINE overlaps the update with in-flight sampling when possible.

Response

Weights-sync operation details

idstring required

Operation ID

status'TRAINING_OPERATION_STATUS_UNSPECIFIED' | 'TRAINING_OPERATION_STATUS_PENDING' | 'TRAINING_OPERATION_STATUS_RUNNING' | 'TRAINING_OPERATION_STATUS_COMPLETED' | 'TRAINING_OPERATION_STATUS_FAILED' required

Example response

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "error": {
    "message": "Operation timed out"
  }
}

Changes