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: 'KVCacheInputs[Buffer, Buffer] | None' = None, lora_ids: 'Buffer | None' = None, lora_ranks: 'Buffer | None' = None, hidden_states: 'Buffer | list[Buffer] | None' = None)

source

Bases: ModelInputs

Parameters:

next_tokens_batch (Buffer)
attention_mask (Buffer)
kv_cache_inputs (KVCacheInputs[Buffer, Buffer] | None)
lora_ids (Buffer | None)
lora_ranks (Buffer | None)
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, pipeline_config)

source

Bases: ArchConfig

Configuration for Bert models.

Parameters:

dtype (DType)
device (DeviceRef)
pool_embeddings (bool)
huggingface_config (AutoConfig)
pipeline_config (PipelineConfig)

`device`

device: DeviceRef

source

`dtype`

dtype: DType

source

`get_max_seq_len()`

get_max_seq_len()

source

Returns the default maximum sequence length for the model.

Subclasses should determine whether this value can be overridden by setting the --max-length (pipeline_config.model.max_length) flag.

Return type:: int

`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

`pipeline_config`

pipeline_config: PipelineConfig

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)

source

Bases: PipelineModel[TextContext]

Parameters:

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

`calculate_max_seq_len()`

classmethod calculate_max_seq_len(pipeline_config, huggingface_config)

source

Calculates the optimal max sequence length for the model.

Models are expected to implement this method. The following example shows how to implement it for a Mistral model:

class MistralModel(PipelineModel):
    @classmethod
    def calculate_max_seq_len(cls, pipeline_config, huggingface_config) -> int:
        try:
            return upper_bounded_default(
                upper_bound=huggingface_config.max_seq_len,
                default=pipeline_config.model.max_length,
            )
        except ValueError as e:
            raise ValueError(
                "Unable to infer max_length for Mistral, the provided "
                f"max_length ({pipeline_config.model.max_length}) exceeds the "
                f"model's max_seq_len ({huggingface_config.max_seq_len})."
            ) from e

Parameters:

pipeline_config (PipelineConfig) – Configuration for the pipeline.
huggingface_config (AutoConfig) – Hugging Face model configuration.

Returns:

The maximum sequence length to use.

Return type:

int

`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.

`load_model()`

load_model(session)

source

Parameters:: session (InferenceSession)
Return type:: Model

`prepare_initial_token_inputs()`

prepare_initial_token_inputs(replica_batches, kv_cache_inputs=None, return_n_logits=1)

source

Prepares the initial inputs to be passed to execute().

The inputs and functionality can vary per model. For example, model inputs could include encoded tensors, unique IDs per tensor when using a KV cache manager, and kv_cache_inputs (or None if the model does not use KV cache). This method typically batches encoded tensors, claims a KV cache slot if needed, and returns the inputs and caches.

Parameters:

replica_batches (Sequence[Sequence[TextContext]])
kv_cache_inputs (KVCacheInputs[Buffer, Buffer] | None)
return_n_logits (int)

Return type:

BertInputs

`prepare_next_token_inputs()`

prepare_next_token_inputs(next_tokens, prev_model_inputs)

source

Prepares the secondary inputs to be passed to execute().

While prepare_initial_token_inputs is responsible for managing the initial inputs. This function is responsible for updating the inputs, for each step in a multi-step execution pattern.

Parameters:

next_tokens (Buffer)
prev_model_inputs (ModelInputs)

Return type:

BertInputs

BertInputs​

attention_mask​

next_tokens_batch​

BertModelConfig​

device​

dtype​

get_max_seq_len()​

huggingface_config​

initialize()​

pipeline_config​

pool_embeddings​

BertPipelineModel​

calculate_max_seq_len()​

execute()​

load_model()​

prepare_initial_token_inputs()​

prepare_next_token_inputs()​

`BertInputs`

`attention_mask`

`next_tokens_batch`

`BertModelConfig`

`device`

`dtype`

`get_max_seq_len()`

`huggingface_config`

`initialize()`

`pipeline_config`

`pool_embeddings`

`BertPipelineModel`

`calculate_max_seq_len()`

`execute()`

`load_model()`

`prepare_initial_token_inputs()`

`prepare_next_token_inputs()`