LinkLlmClusters

Applicability

Product	Supported (Yes/No)
Atlas 350 Accelerator Card	No
Atlas A3 training product/Atlas A3 inference product	Yes
Atlas A2 training product/Atlas A2 inference product	Yes
Atlas 200I/500 A2 inference product	No
Atlas inference product	No
Atlas training product	No

Note: For the Atlas A2 training product/Atlas A2 inference product, only the Atlas 800I A2 inference server and A200I A2 Box heterogeneous subrack are supported.

Function Description

Establishes links between devices.

Prototype

Status LinkLlmClusters(const std::vector<ClusterInfo> &clusters, std::vector<Status> &rets, int32_t timeout_in_millis = 1000)

Parameters

Parameter	Input/Output	Description
clusters	Input	Information about the clusters for which links are to be established. The type is ClusterInfo.
rets	Output	Link establishment result of each cluster.
timeout_in_millis	Input	Link establishment timeout interval, in milliseconds. The default value is 1000.

Returns

LLM_SUCCESS: A success message is returned only when links are successfully established for all clusters.
Other values: Link establishment failed. Check the link establishment result of each cluster.

Exception Handling

LLM_PROCESSING_LINK: The API is protected by a lock. When multiple threads of an LLM-DataDist instance call the link establishment API, the calls are executed serially. If the waiting time of other threads exceeds the configured timeout period, an error is reported and the threads exit.
LLM_ALREADY_LINK: The incremental cluster has already established a link with the full cluster.
LLM_LINK_FAILED: A link fails to be established.
LLM_CLUSTER_NUM_EXCEED_LIMIT: The number of clusters for link establishment exceeds the upper limit. The current number is 16.

Constraints

This API must be called only after the Initialize API is called to complete initialization when the role is Decoder.

Parent topic: LlmDataDist APIs