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 class

GraphPipelineModel

GraphPipelineModel

class max.pipelines.lib.GraphPipelineModel(pipeline_config, session, devices, kv_cache_config, weights, adapter, return_logits, *, memory_plan, return_hidden_states=ReturnHiddenStates.NONE, max_batch_size=1)

source

Bases: PipelineModel[BaseContextType, _ModelConfigT, Model]

Graph-API pipeline model without KV cache.

Subclasses implement _build_graph_for_compile() and optionally _create_model_config() and _wire_batch_processor().

Parameters:

• pipeline_config (PipelineConfig)
• session (InferenceSession)
• devices (list[Device])
• kv_cache_config (KVCacheConfig)
• weights (Weights)
• adapter (WeightsAdapter | None)
• return_logits (ReturnLogits)
• memory_plan (MemoryPlan)
• return_hidden_states (ReturnHiddenStates)
• max_batch_size (int)

load_model()

load_model(session)

source

Load weights, build the graph, compile, and wire the batch processor.

Parameters:

session (InferenceSession)

Return type:

Model

state_dict

state_dict: dict[str, Any]

source