You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.
Platform-managed worker communications. Only disaggregated KV transfer is supported. Omit or set null to preserve the legacy connector configuration.
[optional]
model
str
served_model_name
str
[optional]
extra_args
str
Extra worker CLI arguments as a single shell-style string, split into argv with POSIX shell quoting (shlex). Backslash is an escape character, so `\` is consumed unless quoted: e.g. `--regex \d+` reaches the worker as `d+`. Wrap literal backslashes in single quotes (`--regex '\d+'`). Unbalanced quotes or a trailing backslash are rejected.
[optional]
Example
fromplatform_api_python_client.models.unified_write_deployment_requestimportUnifiedWriteDeploymentRequest# TODO update the JSON string belowjson="{}"# create an instance of UnifiedWriteDeploymentRequest from a JSON stringunified_write_deployment_request_instance=UnifiedWriteDeploymentRequest.from_json(json)
# print the JSON string representation of the objectprint(UnifiedWriteDeploymentRequest.to_json())
# convert the object into a dictunified_write_deployment_request_dict=unified_write_deployment_request_instance.to_dict()
# create an instance of UnifiedWriteDeploymentRequest from a dictunified_write_deployment_request_from_dict=UnifiedWriteDeploymentRequest.from_dict(unified_write_deployment_request_dict)