For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python function

uses_expert_parallel_exchange

uses_expert_parallel_exchange()

max.pipelines.lib.registration_runtime.uses_expert_parallel_exchange(config)

source

Returns whether expert sharding requires exchange initialization.

Parameters:

config (object)

Return type:

bool