LLMConfig Constructor

Applicability

Product	Supported (√/x)
Atlas 350 Accelerator Card	x
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas 200I/500 A2 inference product	x
Atlas inference product	x
Atlas training product	x

Note: For 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

Constructs an LLMConfig instance, which provides the configuration item dictionary required by init. Using this class simplifies the construction of the configuration dictionary.

Decode and Prompt can bidirectionally pull the KV cache. The APIs in this mode include enable_cache_manager, mem_pool_cfg, and listen_ip_info.

Prototype

1	__init__()

Parameters

None

Example

from llm_datadist import LLMConfig
llm_config = LLMConfig()

Returns

LLMConfig instances are returned.

Restrictions

None

Parent topic: LLMConfig