vllm-cpu 0.9.2.post2__cp311-cp311-manylinux_2_17_aarch64.whl

vllm/transformers_utils/configs/minimax_vl_01.py

@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""MiniMaxVL01 model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+from transformers.models.auto import CONFIG_MAPPING
+
+from .minimax_text_01 import MiniMaxText01Config
+
+
+class MiniMaxVL01Config(PretrainedConfig):
+    model_type = "minimax_vl_01"
+
+    def __init__(
+        self,
+        vision_config=None,
+        text_config=None,
+        ignore_index=-100,
+        image_token_index=32000,
+        projector_hidden_act="gelu",
+        vision_feature_select_strategy="default",
+        vision_feature_layer=-2,
+        image_grid_pinpoints=None,
+        tie_word_embeddings=False,
+        image_seq_length=576,
+        **kwargs,
+    ):
+        self.ignore_index = ignore_index
+        self.image_token_index = image_token_index
+        self.projector_hidden_act = projector_hidden_act
+        self.image_seq_length = image_seq_length
+
+        if vision_feature_select_strategy not in ["default", "full"]:
+            raise ValueError("vision_feature_select_strategy should " +
+                             "be one of 'default', 'full'." +
+                             f"Got: {vision_feature_select_strategy}")
+
+        self.vision_feature_select_strategy = vision_feature_select_strategy
+        self.vision_feature_layer = vision_feature_layer
+        image_grid_pinpoints = (
+            image_grid_pinpoints if image_grid_pinpoints is not None else
+            [[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]])
+        self.image_grid_pinpoints = image_grid_pinpoints
+
+        if isinstance(vision_config, dict):
+            if "model_type" not in vision_config:
+                vision_config["model_type"] = "clip_vision_model"
+            vision_config = CONFIG_MAPPING[vision_config["model_type"]](
+                **vision_config)
+        elif vision_config is None:
+            vision_config = CONFIG_MAPPING["clip_vision_model"](
+                intermediate_size=4096,
+                hidden_size=1024,
+                patch_size=14,
+                image_size=336,
+                num_hidden_layers=24,
+                num_attention_heads=16,
+                vocab_size=32000,
+                projection_dim=768,
+            )
+
+        self.vision_config = vision_config
+
+        if text_config is not None:
+            text_config = MiniMaxText01Config(**text_config)
+        else:
+            text_config = MiniMaxText01Config()
+
+        self.text_config = text_config
+
+        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)

vllm/transformers_utils/configs/mllama.py

@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from transformers.models.mllama import configuration_mllama as mllama_hf_config
+
+
+class MllamaTextConfig(mllama_hf_config.MllamaTextConfig):
+    '''
+    Use this class to override is_encoder_decoder:
+    - transformers regards mllama as is_encoder_decoder=False
+    - vllm needs is_encoder_decoder=True to enable cross-attention
+    '''
+
+    def __init__(
+        self,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.is_encoder_decoder = True
+
+
+class MllamaConfig(mllama_hf_config.MllamaConfig):
+
+    def __init__(
+        self,
+        text_config=None,
+        **kwargs,
+    ):
+        if isinstance(text_config, dict):
+            text_config = MllamaTextConfig(**text_config)
+        super().__init__(text_config=text_config, **kwargs)

vllm/transformers_utils/configs/mlp_speculator.py

@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+from typing import Optional
+
+from transformers import PretrainedConfig
+
+
+class MLPSpeculatorConfig(PretrainedConfig):
+    model_type = "mlp_speculator"
+
+    attribute_map = {
+        "hidden_size": "emb_dim",
+    }
+
+    def __init__(self,
+                 vocab_size: int = 32000,
+                 emb_dim: int = 4096,
+                 inner_dim: int = 0,
+                 n_predict: int = 3,
+                 top_k_tokens_per_head: Optional[list[int]] = None,
+                 n_candidates: int = 5,
+                 tie_weights: bool = False,
+                 scale_input: bool = False,
+                 **kwargs):
+        """
+        Initialize an MLPSpeculatorConfig
+
+        Args:
+            vocab_size: int
+                the model vocab size
+            emb_dim: int
+                the model embedding dimension
+            inner_dim: int
+                the inner dimension of the model. If 0, will be the emb_dim.
+            n_predict: int
+                the number of lookaheads for the speculator
+            top_k_tokens_per_head: list[int]
+                Number of tokens to consider from each head when forming the
+                candidate tree.
+                For each candidate branch in the tree, head n produces topk[n]
+                additional sub-branches.
+                NOTE: This parameter is currently unused.
+            n_candidates: int
+                number of child candidates to create per sequence
+            tie_weights: bool
+                If true, use a single set of weights for every model
+                head/stage after the first. The initial projection
+                from the base model may have a different size, so that
+                stays separate.
+            scale_input: bool
+                if True, will scale the initial hidden states from
+                the base model.
+        """
+        if top_k_tokens_per_head is None:
+            top_k_tokens_per_head = [5, 4, 3]
+        assert len(top_k_tokens_per_head) == n_predict
+        self.vocab_size = vocab_size
+        self.emb_dim = emb_dim
+        self.inner_dim = inner_dim
+        self.n_predict = n_predict
+        self.top_k_tokens_per_head = top_k_tokens_per_head
+        self.n_candidates = n_candidates
+        self.num_lookahead_tokens = n_predict
+        self.tie_weights = tie_weights
+        self.scale_input = scale_input
+
+        super().__init__(**kwargs)

vllm/transformers_utils/configs/moonvit.py

@@ -0,0 +1,33 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+# Adapted from https://huggingface.co/moonshotai/Kimi-VL-A3B-Instruct/blob/main/configuration_kimi_vl.py
+from transformers.configuration_utils import PretrainedConfig
+
+
+class MoonViTConfig(PretrainedConfig):
+    model_type = "moonvit"
+
+    def __init__(
+            self,
+            patch_size: int = 14,
+            init_pos_emb_height: int = 64,
+            init_pos_emb_width: int = 64,
+            num_attention_heads: int = 16,
+            num_hidden_layers: int = 27,
+            hidden_size: int = 1152,
+            intermediate_size: int = 4304,
+            merge_kernel_size: tuple[int, int] = (2, 2),
+            **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.patch_size = patch_size
+        # Positional embedding config
+        self.init_pos_emb_height = init_pos_emb_height
+        self.init_pos_emb_width = init_pos_emb_width
+        # Transformer config
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        # Patch merger config
+        self.merge_kernel_size = merge_kernel_size

vllm/transformers_utils/configs/mpt.py

@@ -0,0 +1,180 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+# Copied from
+# https://huggingface.co/mosaicml/mpt-7b/blob/main/configuration_mpt.py
+"""A HuggingFace-style model configuration."""
+import warnings
+from typing import Any, Optional, Union
+
+from transformers import PretrainedConfig
+
+attn_config_defaults: dict = {
+    'attn_type': 'multihead_attention',
+    'attn_pdrop': 0.0,
+    'attn_impl': 'triton',
+    'qk_ln': False,
+    'clip_qkv': None,
+    'softmax_scale': None,
+    'prefix_lm': False,
+    'attn_uses_sequence_id': False,
+    'alibi': False,
+    'alibi_bias_max': 8
+}
+ffn_config_defaults: dict = {'ffn_type': 'mptmlp'}
+init_config_defaults: dict = {
+    'name': 'kaiming_normal_',
+    'fan_mode': 'fan_in',
+    'init_nonlinearity': 'relu',
+    'init_div_is_residual': True,
+    'emb_init_std': None,
+    'emb_init_uniform_lim': None,
+    'init_std': None,
+    'init_gain': 0.0
+}
+
+
+class MPTConfig(PretrainedConfig):
+    model_type = 'mpt'
+    attribute_map = {
+        'num_attention_heads': 'n_heads',
+        'hidden_size': 'd_model',
+        'num_hidden_layers': 'n_layers',
+    }
+
+    # pylint: disable=dangerous-default-value
+    def __init__(self,
+                 d_model: int = 2048,
+                 n_heads: int = 16,
+                 n_layers: int = 24,
+                 expansion_ratio: int = 4,
+                 max_seq_len: int = 2048,
+                 vocab_size: int = 50368,
+                 resid_pdrop: float = 0.0,
+                 emb_pdrop: float = 0.0,
+                 learned_pos_emb: bool = True,
+                 attn_config: dict = attn_config_defaults,
+                 ffn_config: dict = ffn_config_defaults,
+                 init_device: str = 'cpu',
+                 logit_scale: Optional[Union[float, str]] = None,
+                 no_bias: bool = False,
+                 embedding_fraction: float = 1.0,
+                 norm_type: str = 'low_precision_layernorm',
+                 use_cache: bool = False,
+                 init_config: dict = init_config_defaults,
+                 fc_type: str = 'torch',
+                 verbose: Optional[int] = None,
+                 **kwargs: Any):
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.expansion_ratio = expansion_ratio
+        self.max_seq_len = max_seq_len
+        self.vocab_size = vocab_size
+        self.resid_pdrop = resid_pdrop
+        self.emb_pdrop = emb_pdrop
+        self.learned_pos_emb = learned_pos_emb
+        self.attn_config = attn_config
+        self.ffn_config = ffn_config
+        self.init_device = init_device
+        self.logit_scale = logit_scale
+        self.no_bias = no_bias
+        self.embedding_fraction = embedding_fraction
+        self.norm_type = norm_type
+        self.use_cache = use_cache
+        self.init_config = init_config
+        self.fc_type = fc_type
+        if verbose is not None:
+            warnings.warn(DeprecationWarning(
+                'verbose argument for MPTConfig is now ignored and '
+                'will be removed. Use python_log_level instead.'),
+                          stacklevel=2)
+        if 'name' in kwargs:
+            del kwargs['name']
+        if 'loss_fn' in kwargs:
+            del kwargs['loss_fn']
+        if self.attn_config.get('alibi', False):
+            self.learned_pos_emb = False
+            warnings.warn(
+                f'alibi is turned on, setting `learned_pos_emb` '
+                f'to {self.learned_pos_emb}`',
+                stacklevel=2)
+        super().__init__(**kwargs)
+        self._validate_config()
+
+    def _set_config_defaults(
+            self, config: dict[str, Any],
+            config_defaults: dict[str, Any]) -> dict[str, Any]:
+        for (k, v) in config_defaults.items():
+            if k not in config:
+                config[k] = v
+        return config
+
+    def _validate_config(self) -> None:
+        self.attn_config = self._set_config_defaults(self.attn_config,
+                                                     attn_config_defaults)
+        self.ffn_config = self._set_config_defaults(self.ffn_config,
+                                                    ffn_config_defaults)
+        self.init_config = self._set_config_defaults(self.init_config,
+                                                     init_config_defaults)
+        if self.d_model % self.n_heads != 0:
+            raise ValueError('d_model must be divisible by n_heads')
+        if any(
+                prob < 0 or prob > 1 for prob in
+            [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop
+             ]):
+            raise ValueError(
+                "self.attn_config['attn_pdrop'], resid_pdrop, emb_pdrop are "
+                "probabilities and must be between 0 and 1")
+        if self.attn_config['attn_impl'] not in ['torch', 'flash', 'triton']:
+            raise ValueError(
+                f"Unknown attn_impl={self.attn_config['attn_impl']}")
+        if self.attn_config['prefix_lm'] and self.attn_config[
+                'attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError(
+                'prefix_lm only implemented with torch and triton attention.')
+        if self.attn_config['alibi'] and self.attn_config['attn_impl'] not in [
+                'torch', 'triton'
+        ]:
+            raise NotImplementedError(
+                'alibi only implemented with torch and triton attention.')
+        if self.attn_config['attn_uses_sequence_id'] and self.attn_config[
+                'attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError(
+                'attn_uses_sequence_id only implemented with torch '
+                'and triton attention.')
+        if self.embedding_fraction > 1 or self.embedding_fraction <= 0:
+            raise ValueError(
+                'model.embedding_fraction must be between 0 (exclusive) '
+                'and 1 (inclusive)!')
+        if isinstance(self.logit_scale,
+                      str) and self.logit_scale != 'inv_sqrt_d_model':
+            raise ValueError(
+                f"self.logit_scale={self.logit_scale!r} is not recognized as "
+                "an option; use numeric value or 'inv_sqrt_d_model'.")
+        if self.init_config.get('name', None) is None:
+            raise ValueError(
+                f"self.init_config={self.init_config!r} 'name' needs to be set."
+            )
+        if not self.learned_pos_emb and (not self.attn_config['alibi']):
+            warnings.warn(
+                'Positional information not being provided to the model.',
+                stacklevel=2)
+        if self.fc_type == 'te' or self.ffn_config['ffn_type'] == 'te_ln_mlp':
+            try:
+                # pylint: disable=import-outside-toplevel
+                import transformer_engine.pytorch as te
+                del te
+            except Exception as exc:
+                raise ImportError(
+                    'TransformerEngine import fail. `fc_type: te` requires '
+                    'TransformerEngine be installed. '
+                    'The required version of transformer_engine also requires '
+                    'FlashAttention v1.0.6 is installed:\n'
+                    'pip install flash-attn==1.0.6 --no-build-isolation \n'
+                    'pip install git+https://github.com/NVIDIA/TransformerEngine.git@144e4888b2cdd60bd52e706d5b7a79cb9c1a7156'
+                ) from exc
+        if self.ffn_config['ffn_type'] == 'mptmlp':
+            self.ffn_config['fc_type'] = self.fc_type
+        elif self.ffn_config['ffn_type'] == 'te_ln_mlp':
+            self.ffn_config['bias'] = not self.no_bias

vllm/transformers_utils/configs/nemotron.py

@@ -0,0 +1,205 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
+# Copyright 2024 HuggingFace Inc. team. All rights reserved.
+# Copyright (c) 2024, NVIDIA CORPORATION. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Nemotron model configuration"""
+
+from transformers import PretrainedConfig
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+
+class NemotronConfig(PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a
+    [`NemotronModel`]. It is used to instantiate an Nemotron model
+    according to the specified arguments, defining the model architecture.
+    Instantiating a configuration with the defaults will yield a similar
+    configuration to that of the Nemotron-8B.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be
+    used to control the model outputs. Read the documentation from
+    [`PretrainedConfig`] for more information.
+
+
+    Args:
+        vocab_size (`int`, *optional*, defaults to 256000):
+            Vocabulary size of the Nemotron model. Defines the number of
+            different tokens that can be represented by the
+            `inputs_ids` passed when calling [`NemotronModel`]
+        hidden_size (`int`, *optional*, defaults to 6144):
+            Dimension of the hidden representations.
+        intermediate_size (`int`, *optional*, defaults to 24576):
+            Dimension of the MLP representations.
+        num_hidden_layers (`int`, *optional*, defaults to 32):
+            Number of hidden layers in the Transformer decoder.
+        num_attention_heads (`int`, *optional*, defaults to 48):
+            Number of attention heads for each attention layer in the
+            Transformer decoder.
+        head_dim (`int`, *optional*):
+            Projection weights dimension in multi-head attention. Set to
+            hidden_size // num_attention_heads if None
+        num_key_value_heads (`int`, *optional*):
+            This is the number of key_value heads that should be used to
+            implement Grouped Query Attention. If
+            `num_key_value_heads=num_attention_heads`, the model will use
+            Multi Head Attention (MHA), if
+            `num_key_value_heads=1 the model will use Multi Query Attention
+            (MQA) otherwise GQA is used. When converting a multi-head
+            checkpoint to a GQA checkpoint, each group key and value
+            head should be constructed by meanpooling all the original
+            heads within that group. For more details checkout 
+            [this paper](https://arxiv.org/pdf/2305.13245.pdf). If it
+            is not specified, will default to `num_attention_heads`.
+        hidden_act (`str` or `function`, *optional*, defaults to `"relu2"`):
+            The non-linear activation function (function or string) in the
+            decoder.
+        max_position_embeddings (`int`, *optional*, defaults to 4096):
+            The maximum sequence length that this model might ever be used
+            with.
+        initializer_range (`float`, *optional*, defaults to 0.0134):
+            The standard deviation of the truncated_normal_initializer for
+            initializing all weight matrices.
+        norm_eps (`float`, *optional*, defaults to 1e-05):
+            The epsilon used by the normalization layers.
+        use_cache (`bool`, *optional*, defaults to `True`):
+            Whether or not the model should return the last key/values
+            attentions (not used by all models). Only relevant if
+            `config.is_decoder=True`.
+        pad_token_id (`int`, *optional*):
+            Padding token id.
+        bos_token_id (`int`, *optional*, defaults to 2):
+            Beginning of stream token id.
+        eos_token_id (`int`, *optional*, defaults to 3):
+            End of stream token id.
+        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
+            Whether to tie weight embeddings
+        rope_theta (`float`, *optional*, defaults to 10000.0):
+            The base period of the RoPE embeddings.
+        partial_rotary_factor (`float`, *optional*, defaults to 0.5):
+            Percentage of the query and keys which will have rotary embedding.
+        attention_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in the query, key, value and output
+            projection layers during self-attention.
+        attention_dropout (`float`, *optional*, defaults to 0.0):
+            The dropout ratio for the attention probabilities.
+        mlp_bias (`bool`, *optional*, defaults to `False`):
+            Whether to use a bias in up_proj and down_proj layers in the MLP
+            layers.
+
+    ```python
+    >>> from transformers import NemotronModel, NemotronConfig
+    >>> # Initializing a Nemotron nemotron-15b style configuration
+    >>> configuration = NemotronConfig()
+    >>> # Initializing a model from the nemotron-15b style configuration
+    >>> model = NemotronModel(configuration)
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
+
+    model_type = "nemotron"
+    keys_to_ignore_at_inference = ["past_key_values"]
+
+    def __init__(
+        self,
+        vocab_size=256000,
+        hidden_size=6144,
+        intermediate_size=24576,
+        num_hidden_layers=32,
+        num_attention_heads=48,
+        head_dim=None,
+        num_key_value_heads=None,
+        hidden_act="relu2",
+        max_position_embeddings=4096,
+        initializer_range=0.0134,
+        norm_eps=1e-5,
+        use_cache=True,
+        pad_token_id=None,
+        bos_token_id=2,
+        eos_token_id=3,
+        tie_word_embeddings=False,
+        rope_theta=10000.0,
+        rope_scaling=None,
+        partial_rotary_factor=0.5,
+        attention_bias=False,
+        attention_dropout=0.0,
+        mlp_bias=False,
+        **kwargs,
+    ):
+        self.vocab_size = vocab_size
+        self.max_position_embeddings = max_position_embeddings
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        head_dim = head_dim or kwargs.get("kv_channels")
+        self.head_dim = head_dim if head_dim is not None else (
+            hidden_size // num_attention_heads)
+
+        # for backward compatibility
+        if num_key_value_heads is None:
+            num_key_value_heads = num_attention_heads
+
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.initializer_range = initializer_range
+        self.norm_eps = norm_eps
+        self.use_cache = use_cache
+        self.rope_theta = rope_theta
+        self.rope_scaling = rope_scaling
+        # for backward compatibility
+        partial_rotary_factor = kwargs.get("rope_percent") or kwargs.get(
+            "rope_percentage") or partial_rotary_factor
+        self.partial_rotary_factor = partial_rotary_factor
+        self._rope_scaling_validation()
+        self.attention_bias = attention_bias
+        self.attention_dropout = attention_dropout
+        self.mlp_bias = mlp_bias
+
+        super().__init__(
+            pad_token_id=pad_token_id,
+            bos_token_id=bos_token_id,
+            eos_token_id=eos_token_id,
+            tie_word_embeddings=tie_word_embeddings,
+            **kwargs,
+        )
+
+    def _rope_scaling_validation(self):
+        """
+        Validate the `rope_scaling` configuration.
+        """
+        if self.rope_scaling is None:
+            return
+
+        if not isinstance(self.rope_scaling, dict) or len(
+                self.rope_scaling) != 2:
+            raise ValueError(
+                "`rope_scaling` must be a dictionary with two fields, "
+                f"`type` and `factor`, got {self.rope_scaling}")
+        rope_scaling_type = self.rope_scaling.get("type", None)
+        rope_scaling_factor = self.rope_scaling.get("factor", None)
+        if rope_scaling_type is None or rope_scaling_type not in [
+                "linear", "dynamic"
+        ]:
+            raise ValueError(
+                "`rope_scaling`'s type field must be one of ['linear', "
+                f"'dynamic'], got {rope_scaling_type}")
+        if rope_scaling_factor is None or not isinstance(
+                rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
+            raise ValueError(
+                "`rope_scaling`'s factor field must be a float > 1, got "
+                f"{rope_scaling_factor}")