IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
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

grouped_matmul_bounds

grouped_matmul_bounds()​

max.nn.ep.grouped_matmul_bounds(config)

source

Returns the grouped matmul’s host bounds for the received tokens.

Parameters:

config (EPConfig) – The expert-parallel configuration.

Returns:

the most rows a device can receive for one expert, then the number of experts on a device, counting a fused shared expert.

Return type:

A uint32 host tensor of shape (2,)