model_config

This module defines the model_config format.

This format can be converted from huggingface, nemo or modelopt-quantized model. And we will build tensorrt_llm engine from the context saved with this format.

Classes

AttentionConfig	The attention layer config.
ConvConfig	The Conv layer config.
DecoderLayerConfig	The decoder layer config.
EmbeddingConfig	The embedding layer config.
ExpertConfig	The Expert config.
LayernormConfig	The layernorm layer config.
LinearActConfig	The linear + activation layer config.
LinearConfig	The linear layer config.
MLPConfig	The MLP layer config.
MOEConfig	The Mixture of Expert layer config.
MedusaHeadConfig	The decoder layer config.
ModelConfig	The full LLM model config that includes the full information needed for tensorrt_llm engine building.
QKVConfig	The QKV layer config.
RecurrentConfig	The RecurrentBlock from recurrentgemma.
RgLruConfig	The RG LRU from recurrentgemma.

class AttentionConfig

Bases: object

The attention layer config.

__init__(qkv=None, dense=None, kv_cache_scaling_factor=None, kv_cache_dtype=None, rotary_dim=-inf, clip_qkv=None, rel_attn_table=None)

Parameters:

• qkv (QKVConfig | LinearConfig) –

• dense (LinearConfig) –

• kv_cache_scaling_factor (Tensor) –

• kv_cache_dtype (str | None) –

• rotary_dim (int) –

• clip_qkv (float) –

• rel_attn_table (Tensor) –

Return type:

None

clip_qkv: float = None

dense: LinearConfig = None

kv_cache_dtype: str | None = None

kv_cache_scaling_factor: Tensor = None

qkv: QKVConfig | LinearConfig = None

rel_attn_table: Tensor = None

rotary_dim: int = -inf

class ConvConfig

Bases: object

The Conv layer config.

__init__(quantization=None, weight=None, bias=None)

Parameters:

• quantization (str | None) –

• weight (Tensor) –

• bias (Tensor) –

Return type:

None

bias: Tensor = None

quantization: str | None = None

weight: Tensor = None

class DecoderLayerConfig

Bases: object

The decoder layer config.

__init__(quantization=None, decoder_type='', input_layernorm=None, mlp_layernorm=None, attention=None, recurrent=None, post_layernorm=None, pre_feedforward_layernorm=None, post_feedforward_layernorm=None, mlp=None, num_attention_heads=0, attention_head_size=None, num_kv_heads=0, max_position_embeddings=0, rotary_pct=1.0, use_alibi=False, new_decoder_architecture=False, parallel_attention=False, apply_residual_connection_post_layernorm=False, use_cache=True, chatglm_version='', rope_ratio=1.0, seq_length=0, qwen_type='', rotary_base=0, partial_rotary_factor=0, original_max_position_embeddings=0, longrope_scaling_short_factors=None, longrope_scaling_long_factors=None, mup_attn_multiplier=0, mup_embedding_multiplier=0, mup_use_scaling=0, mup_width_multiplier=0, blocksparse_block_size=0, blocksparse_homo_head_pattern=False, blocksparse_num_local_blocks=0, blocksparse_vertical_stride=0, dense_attention_every_n_layers=0, gegelu_limit=0, longrope_short_mscale=0, longrope_long_mscale=0, moe_num_experts=0, moe_top_k=0, moe_tp_mode=0, moe_renorm_mode=0, alibi_bias_max=0, residual_layernorm=None, residual_mlp=None, rnn_hidden_size=0, logits_soft_cap=0, emb_scale_by_sqrt_dim=False, layer_types=<factory>, attn_replacing_linear=None, mlp_replacing_linear=None, block_config=None, final_logit_softcapping=0, attn_logit_softcapping=0, query_pre_attn_scalar=0, clip_qkv=0, cross_attention=None, cross_attention_layernorm=None, self_attention=None, self_attention_layernorm=None, attention_layernorm=None, rel_attn_max_distance=0, rel_attn_num_buckets=0, rope_scaling=None)

Parameters:

• quantization (str | None) –

• decoder_type (str) –

• input_layernorm (LayernormConfig) –

• mlp_layernorm (LayernormConfig) –

• attention (AttentionConfig) –

• recurrent (RecurrentConfig) –

• post_layernorm (LayernormConfig) –

• pre_feedforward_layernorm (LayernormConfig) –

• post_feedforward_layernorm (LayernormConfig) –

• mlp (MLPConfig | MOEConfig) –

• num_attention_heads (int) –

• attention_head_size (int) –

• num_kv_heads (int) –

• max_position_embeddings (int) –

• rotary_pct (float) –

• use_alibi (bool) –

• new_decoder_architecture (bool) –

• parallel_attention (bool) –

• apply_residual_connection_post_layernorm (bool) –

• use_cache (bool) –

• chatglm_version (str) –

• rope_ratio (float) –

• seq_length (int) –

• qwen_type (str) –

• rotary_base (int) –

• partial_rotary_factor (float) –

• original_max_position_embeddings (int) –

• longrope_scaling_short_factors (List[float]) –

• longrope_scaling_long_factors (List[float]) –

• mup_attn_multiplier (float) –

• mup_embedding_multiplier (float) –

• mup_use_scaling (float) –

• mup_width_multiplier (float) –

• blocksparse_block_size (int) –

• blocksparse_homo_head_pattern (bool) –

• blocksparse_num_local_blocks (int) –

• blocksparse_vertical_stride (int) –

• dense_attention_every_n_layers (int) –

• gegelu_limit (float) –

• longrope_short_mscale (float) –

• longrope_long_mscale (float) –

• moe_num_experts (int) –

• moe_top_k (int) –

• moe_tp_mode (int) –

• moe_renorm_mode (int) –

• alibi_bias_max (int) –

• residual_layernorm (LayernormConfig) –

• residual_mlp (MLPConfig) –

• rnn_hidden_size (int) –

• logits_soft_cap (float) –

• emb_scale_by_sqrt_dim (bool) –

• layer_types (List[str]) –

• attn_replacing_linear (LinearConfig) –

• mlp_replacing_linear (LinearConfig) –

• block_config (dict) –

• final_logit_softcapping (float) –

• attn_logit_softcapping (float) –

• query_pre_attn_scalar (float) –

• clip_qkv (int) –

• cross_attention (AttentionConfig) –

• cross_attention_layernorm (LayernormConfig) –

• self_attention (AttentionConfig) –

• self_attention_layernorm (LayernormConfig) –

• attention_layernorm (LayernormConfig) –

• rel_attn_max_distance (int) –

• rel_attn_num_buckets (int) –

• rope_scaling (dict) –

Return type:

None

alibi_bias_max: int = 0

apply_residual_connection_post_layernorm: bool = False

attention: AttentionConfig = None

attention_head_size: int = None

attention_layernorm: LayernormConfig = None

attn_logit_softcapping: float = 0

attn_replacing_linear: LinearConfig = None

block_config: dict = None

blocksparse_block_size: int = 0

blocksparse_homo_head_pattern: bool = False

blocksparse_num_local_blocks: int = 0

blocksparse_vertical_stride: int = 0

chatglm_version: str = ''

clip_qkv: int = 0

cross_attention: AttentionConfig = None

cross_attention_layernorm: LayernormConfig = None

decoder_type: str = ''

dense_attention_every_n_layers: int = 0

emb_scale_by_sqrt_dim: bool = False

property ffn_hidden_size_local

Returns the ffn hidden size of the transformer model.

final_logit_softcapping: float = 0

gegelu_limit: float = 0

property hidden_size

Returns the hidden size of the transformer model.

input_layernorm: LayernormConfig = None

layer_types: List[str]

logits_soft_cap: float = 0

longrope_long_mscale: float = 0

longrope_scaling_long_factors: List[float] = None

longrope_scaling_short_factors: List[float] = None

longrope_short_mscale: float = 0

max_position_embeddings: int = 0

mlp: MLPConfig | MOEConfig = None

mlp_layernorm: LayernormConfig = None

mlp_replacing_linear: LinearConfig = None

moe_num_experts: int = 0

moe_renorm_mode: int = 0

moe_top_k: int = 0

moe_tp_mode: int = 0

mup_attn_multiplier: float = 0

mup_embedding_multiplier: float = 0

mup_use_scaling: float = 0

mup_width_multiplier: float = 0

new_decoder_architecture: bool = False

num_attention_heads: int = 0

num_kv_heads: int = 0

original_max_position_embeddings: int = 0

parallel_attention: bool = False

partial_rotary_factor: float = 0

post_feedforward_layernorm: LayernormConfig = None

post_layernorm: LayernormConfig = None

pre_feedforward_layernorm: LayernormConfig = None

quantization: str | None = None

query_pre_attn_scalar: float = 0

qwen_type: str = ''

recurrent: RecurrentConfig = None

rel_attn_max_distance: int = 0

rel_attn_num_buckets: int = 0

residual_layernorm: LayernormConfig = None

residual_mlp: MLPConfig = None

rnn_hidden_size: int = 0

rope_ratio: float = 1.0

rope_scaling: dict = None

rotary_base: int = 0

rotary_pct: float = 1.0

self_attention: AttentionConfig = None

self_attention_layernorm: LayernormConfig = None

seq_length: int = 0

use_alibi: bool = False

use_cache: bool = True

class EmbeddingConfig

Bases: object

The embedding layer config.

__init__(weight=None, quantization=None)

Parameters:

• weight (Tensor) –

• quantization (str | None) –

Return type:

None

property hidden_size

Infers the hidden_size from the embedding layer weights shape.

property local_vocab_size

Infers the vocab_size from the embedding layer weights shape.

quantization: str | None = None

weight: Tensor = None

class ExpertConfig

Bases: object

The Expert config.

__init__(fc=None, proj=None)

Parameters:

• fc (LinearConfig) –

• proj (LinearConfig) –

Return type:

None

fc: LinearConfig = None

proj: LinearConfig = None

class LayernormConfig

Bases: object

The layernorm layer config.

__init__(quantization=None, weight=None, bias=None, layernorm_type='', eps=1e-05)

Parameters:

• quantization (str | None) –

• weight (Tensor) –

• bias (Tensor) –

• layernorm_type (str) –

• eps (float) –

Return type:

None

bias: Tensor = None

eps: float = 1e-05

layernorm_type: str = ''

quantization: str | None = None

weight: Tensor = None

class LinearActConfig

Bases: object

The linear + activation layer config.

__init__(linear=None, hidden_act='')

Parameters:

• linear (LinearConfig) –

• hidden_act (str) –

Return type:

None

hidden_act: str = ''

linear: LinearConfig = None

class LinearConfig

Bases: object

The linear layer config.

__init__(quantization=None, linear_type='column', weight=None, bias=None, activation_scaling_factor=None, weights_scaling_factor=None, weights_scaling_factor_2=None, prequant_scaling_factor=None, awq_block_size=0)

Parameters:

• quantization (str | None) –

• linear_type (str) –

• weight (Tensor) –

• bias (Tensor) –

• activation_scaling_factor (Tensor) –

• weights_scaling_factor (Tensor) –

• weights_scaling_factor_2 (Tensor) –

• prequant_scaling_factor (Tensor) –

• awq_block_size (int) –

Return type:

None

activation_scaling_factor: Tensor = None

awq_block_size: int = 0

bias: Tensor = None

linear_type: str = 'column'

prequant_scaling_factor: Tensor = None

quantization: str | None = None

weight: Tensor = None

weights_scaling_factor: Tensor = None

weights_scaling_factor_2: Tensor = None

class MLPConfig

Bases: object

The MLP layer config.

__init__(fc=None, gate=None, proj=None, hidden_act='', merged_fc1_gate=False)

Parameters:

• fc (LinearConfig) –

• gate (LinearConfig) –

• proj (LinearConfig) –

• hidden_act (str) –

• merged_fc1_gate (bool) –

Return type:

None

fc: LinearConfig = None

gate: LinearConfig = None

hidden_act: str = ''

merged_fc1_gate: bool = False

proj: LinearConfig = None

property quantization

Returns merged gat and fc1 quantization.

class MOEConfig

Bases: object

The Mixture of Expert layer config.

__init__(router=None, experts=None, hidden_act='')

Parameters:

• router (LinearConfig) –

• experts (ExpertConfig) –

• hidden_act (str) –

Return type:

None

experts: ExpertConfig = None

property fc

Return the fc module from experts.

hidden_act: str = ''

router: LinearConfig = None

class MedusaHeadConfig

Bases: object

The decoder layer config.

__init__(medusa_layers=None, lm_head=None)

Parameters:

• medusa_layers (List[LinearActConfig]) –

• lm_head (LinearConfig) –

Return type:

None

lm_head: LinearConfig = None

medusa_layers: List[LinearActConfig] = None

class ModelConfig

Bases: object

The full LLM model config that includes the full information needed for tensorrt_llm engine building.

This class includes all the fields that tensorrt_llm supports, but not all of the fields are required. pipeline_parallel > 1 is only supported for TensorRT-LLM checkpoint.

__init__(version=0.0, quantization=None, dtype='float16', vocab_size=0, rank=0, tensor_parallel=1, pipeline_parallel=1, vocab_embedding=None, position_embedding=None, block_embedding=None, ln_embed=None, layers=<factory>, ln_f=None, lm_head=None, share_embedding_table=False, medusa_heads=None, num_medusa_heads=0, num_medusa_layers=0, enc_dec='', encoder_hidden_size=0, encoder_num_heads=0, encoder_head_size=0)

Parameters:

• version (float) –

• quantization (str) –

• dtype (str) –

• vocab_size (int) –

• rank (int) –

• tensor_parallel (int) –

• pipeline_parallel (int) –

• vocab_embedding (EmbeddingConfig) –

• position_embedding (EmbeddingConfig) –

• block_embedding (EmbeddingConfig) –

• ln_embed (LayernormConfig) –

• layers (List[DecoderLayerConfig]) –

• ln_f (LayernormConfig) –

• lm_head (LinearConfig) –

• share_embedding_table (bool) –

• medusa_heads (List[MedusaHeadConfig]) –

• num_medusa_heads (int) –

• num_medusa_layers (int) –

• enc_dec (str) –

• encoder_hidden_size (int) –

• encoder_num_heads (int) –

• encoder_head_size (int) –

Return type:

None

block_embedding: EmbeddingConfig = None

dtype: str = 'float16'

enc_dec: str = ''

encoder_head_size: int = 0

encoder_hidden_size: int = 0

encoder_num_heads: int = 0

property hidden_act

Returns the hidden_act of the model.

property hidden_size

Returns the hidden_size of the model.

layers: List[DecoderLayerConfig]

lm_head: LinearConfig = None

ln_embed: LayernormConfig = None

ln_f: LayernormConfig = None

property max_position_embeddings

Returns the max_position_embedding of the model.

medusa_heads: List[MedusaHeadConfig] = None

property num_attention_heads

Returns the num_attention_heads of the model.

property num_kv_heads

Returns the num_key_value_heads of the model.

num_medusa_heads: int = 0

num_medusa_layers: int = 0

pipeline_parallel: int = 1

position_embedding: EmbeddingConfig = None

quantization: str = None

rank: int = 0

share_embedding_table: bool = False

tensor_parallel: int = 1

version: float = 0.0

vocab_embedding: EmbeddingConfig = None

vocab_size: int = 0

property vocab_size_padded

Returns the padded vocab_size of the model rounds to the tensor_parallel.

class QKVConfig

Bases: object

The QKV layer config.

__init__(q=None, k=None, v=None)

Parameters:

• q (LinearConfig) –

• k (LinearConfig) –

• v (LinearConfig) –

Return type:

None

property activation_scaling_factor

Returns the merged activation_scaling_factor across Q, K and V.

The max of the Q, K, V activation scaling factors is returned.

property awq_block_size

Returns the awq_block_size of this QKV layer.

property bias

The generated linear layer bias.

The Q, K, V bias are concat together to fit the TensorRT-LLM QKV linear layer.

k: LinearConfig = None

property prequant_scaling_factor

Returns the merged prequant_scaling_factor across Q, K and V.

Prequant scaling factors for Q, K, V should be the same. So just return one of them.

q: LinearConfig = None

property quantization

Returns the quantization format of this QKV layer.

v: LinearConfig = None

property weight

The generated linear layer weight.

The Q, K, V weights are concat together to fit the TensorRT-LLM QKV linear layer.

property weights_scaling_factor

Returns the merged weights_scaling_factor across Q, K and V.

If the quantization is FP8, the max of the Q, K, V weight scaling factors is returned. If the quanitzation is INT8_SQ, the concat value is returned.

property weights_scaling_factor_2

Returns the merged weights_scaling_factor_2 across Q, K and V.

weight_scaling_factor_2 is needed for W4A8 AWQ.

class RecurrentConfig

Bases: object

The RecurrentBlock from recurrentgemma.

__init__(linear_y=None, y_bias=None, linear_x=None, linear_out=None, conv1d=None, rg_lru=None)

Parameters:

• linear_y (LinearConfig) –

• y_bias (Tensor) –

• linear_x (LinearConfig) –

• linear_out (LinearConfig) –

• conv1d (ConvConfig) –

• rg_lru (RgLruConfig) –

Return type:

None

conv1d: ConvConfig = None

linear_out: LinearConfig = None

linear_x: LinearConfig = None

linear_y: LinearConfig = None

rg_lru: RgLruConfig = None

y_bias: Tensor = None

class RgLruConfig

Bases: object

The RG LRU from recurrentgemma.

__init__(recurrent_param=None, input_gate=None, recurrent_gate=None)

Parameters:

• recurrent_param (Tensor) –

• input_gate (LinearConfig) –

• recurrent_gate (LinearConfig) –

Return type:

None

input_gate: LinearConfig = None

recurrent_gate: LinearConfig = None

recurrent_param: Tensor = None