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 module

max.pipelines.architectures.mistral

Mistral transformer architecture for text generation.

MistralConfig

class max.pipelines.architectures.mistral.MistralConfig(*, hidden_size, num_attention_heads, num_key_value_heads, num_hidden_layers, head_dim, vocab_size, rope_theta, max_seq_len, rms_norm_eps, feed_forward_length, dtype, kv_params, attention_multiplier, devices, return_logits=ReturnLogits.LAST_TOKEN, quantization_encoding=None)

source

Bases: ArchConfigWithPermissiveMaxSeqLen, ArchConfigWithStoredKVParams, ArchConfigWithKVCache

Configuration for Mistral models.

Parameters:

• hidden_size (int)
• num_attention_heads (int)
• num_key_value_heads (int)
• num_hidden_layers (int)
• head_dim (int)
• vocab_size (int)
• rope_theta (float)
• max_seq_len (int)
• rms_norm_eps (float)
• feed_forward_length (int)
• dtype (DType)
• kv_params (KVCacheParams)
• attention_multiplier (float)
• devices (list[DeviceRef])
• return_logits (ReturnLogits)
• quantization_encoding (SupportedEncoding | None)

DEFAULT_ENCODING

DEFAULT_ENCODING: ClassVar[SupportedEncoding] = 'bfloat16'

source

SUPPORTED_ENCODINGS

SUPPORTED_ENCODINGS: ClassVar[set[SupportedEncoding]] = {'bfloat16'}

source

attention_multiplier

attention_multiplier: float

source

devices

devices: list[DeviceRef]

source

dtype

dtype: DType

source

feed_forward_length

feed_forward_length: int

source

get_max_seq_len()

get_max_seq_len()

source

Returns the resolved maximum sequence length stored on the config.

Return type:

int

head_dim

head_dim: int

source

hidden_size

hidden_size: int

source

initialize()

classmethod initialize(pipeline_config, model_config=None)

source

Initializes a MistralConfig instance from pipeline configuration.

This method creates a config instance with all fields that can be determined from the pipeline configuration.

Parameters:

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

Returns:

An initialized MistralConfig instance.

Return type:

Self

initialize_from_config()

classmethod initialize_from_config(pipeline_config, huggingface_config)

source

Parameters:

• pipeline_config (PipelineConfig)
• huggingface_config (AutoConfig)

Return type:

Self

kv_params

kv_params: KVCacheParams

source

max_seq_len

max_seq_len: int

source

num_attention_heads

num_attention_heads: int

source

num_hidden_layers

num_hidden_layers: int

source

num_key_value_heads

num_key_value_heads: int

source

quantization_encoding

quantization_encoding: SupportedEncoding | None = None

source

return_logits

return_logits: ReturnLogits = 'last_token'

source

Whether to return the last token, all logits, or a variable number of logits.

rms_norm_eps

rms_norm_eps: float

source

rope_theta

rope_theta: float

source

vocab_size

vocab_size: int

source

MistralInputs

class max.pipelines.architectures.mistral.MistralInputs(tokens, input_row_offsets, signal_buffers, return_n_logits, *, kv_cache_inputs=None, lora=None, lora_buffers=(), vision_embeddings=<factory>, vision_scatter_indices=<factory>, hidden_states=None)

source

Bases: ModelInputs

A class representing inputs for the Mistral model.

This class encapsulates the input tensors required for the Mistral model execution:

• tokens: A tensor containing the input token IDs
• input_row_offsets: A tensor containing the offsets for each row in the ragged input sequence
• return_n_logits: A tensor containing the number of expected token logits.

Parameters:

• tokens (Buffer)
• input_row_offsets (Buffer)
• signal_buffers (list[Buffer])
• return_n_logits (Buffer)
• kv_cache_inputs (KVCacheInputsInterface[Buffer, Buffer] | None)
• lora (LoRAInputs | None)
• lora_buffers (tuple[Buffer, ...])
• vision_embeddings (list[Buffer])
• vision_scatter_indices (list[Buffer])
• hidden_states (Buffer | list[Buffer] | None)

input_row_offsets

input_row_offsets: Buffer

source

return_n_logits

return_n_logits: Buffer

source

signal_buffers

signal_buffers: list[Buffer]

source

Device buffers used for synchronization in communication collectives.

tokens

tokens: Buffer

source

MistralModel

class max.pipelines.architectures.mistral.MistralModel(pipeline_config, session, devices, kv_cache_config, weights, adapter=None, return_logits=ReturnLogits.LAST_TOKEN, max_batch_size=1)

source

Bases: GraphPipelineModelWithKVCache[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 MistralBatchProcessor

calculate_max_seq_len()

classmethod calculate_max_seq_len(pipeline_config, huggingface_config)

source

Bounds max_length by max_position_embeddings (config is permissive).

Parameters:

• pipeline_config (PipelineConfig)
• huggingface_config (AutoConfig)

Return type:

int

execute()

execute(model_inputs)

source

Runs the graph.

Parameters:

model_inputs (ModelInputs)

Return type:

ModelOutputs

load_model()

load_model(session)

source

Build, compile, and load the model graph into session.

Parameters:

session (InferenceSession)

Return type:

Model

model

model: Model

source

Compiled and initialized model ready for inference.

model_config_cls

model_config_cls

source

alias of MistralConfig