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

Python module

max.pipelines.architectures.bert

BERT sentence transformer architecture for embeddings generation.

`BertInputs`

class max.pipelines.architectures.bert.BertInputs(next_tokens_batch: 'Buffer', attention_mask: 'Buffer', *, kv_cache_inputs: 'KVCacheInputsInterface[Buffer, Buffer] | None' = None, lora: 'LoRAInputs | None' = None, vision_embeddings: 'list[Buffer]' = <factory>, vision_scatter_indices: 'list[Buffer]' = <factory>, hidden_states: 'Buffer | list[Buffer] | None' = None)

source

Bases: ModelInputs

Parameters:

next_tokens_batch (Buffer)
attention_mask (Buffer)
kv_cache_inputs (KVCacheInputsInterface[Buffer, Buffer] | None)
lora (LoRAInputs | None)
vision_embeddings (list[Buffer])
vision_scatter_indices (list[Buffer])
hidden_states (Buffer | list[Buffer] | None)

`attention_mask`

attention_mask: Buffer

source

`next_tokens_batch`

next_tokens_batch: Buffer

source

`BertModelConfig`

class max.pipelines.architectures.bert.BertModelConfig(*, dtype, device, pool_embeddings, huggingface_config, max_seq_len)

source

Bases: ArchConfigWithBoundedMaxSeqLen, ArchConfig

Configuration for Bert models.

Parameters:

dtype (DType)
device (DeviceRef)
pool_embeddings (bool)
huggingface_config (AutoConfig)
max_seq_len (int)

`device`

device: DeviceRef

source

`dtype`

dtype: DType

source

`huggingface_config`

huggingface_config: AutoConfig

source

`initialize()`

classmethod initialize(pipeline_config, model_config=None)

source

Initializes a BertModelConfig instance from pipeline configuration.

Parameters:

pipeline_config (PipelineConfig) – The MAX Engine pipeline configuration.
model_config (MAXModelConfig | None)

Returns:

An initialized BertModelConfig instance.

Return type:

Self

`max_seq_len`

max_seq_len: int

source

`pool_embeddings`

pool_embeddings: bool

source

`BertPipelineModel`

class max.pipelines.architectures.bert.BertPipelineModel(pipeline_config, session, devices, kv_cache_config, weights, adapter=None, return_logits=ReturnLogits.ALL, max_batch_size=1)

source

Bases: GraphPipelineModel[TextContext]

Parameters:

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

`batch_processor_cls`

batch_processor_cls

source

alias of BertBatchProcessor

`execute()`

execute(model_inputs)

source

Executes the graph with the given inputs.

Parameters:: model_inputs (ModelInputs) – The model inputs to execute, containing tensors and any other required data for model execution.
Returns:: ModelOutputs containing the pipeline’s output tensors.
Return type:: ModelOutputs

This is an abstract method that must be implemented by concrete PipelineModels to define their specific execution logic.

`model`

model: Model

source

`model_config_cls`

model_config_cls

source

alias of BertModelConfig

BertInputs​

attention_mask​

next_tokens_batch​

BertModelConfig​

device​

dtype​

huggingface_config​

initialize()​

max_seq_len​

pool_embeddings​

BertPipelineModel​

batch_processor_cls​

execute()​

model​

model_config_cls​

`BertInputs`

`attention_mask`

`next_tokens_batch`

`BertModelConfig`

`device`

`dtype`

`huggingface_config`

`initialize()`

`max_seq_len`

`pool_embeddings`

`BertPipelineModel`

`batch_processor_cls`

`execute()`

`model`

`model_config_cls`