[Core] Move multimodal placeholder from chat utils to model definition (#20355)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-07-03 08:18:30 +00:00
committed by GitHub
parent cb97f2bfc5
commit b024a42e93
54 changed files with 396 additions and 155 deletions
+2 -1
View File
@@ -18,7 +18,7 @@ from vllm.model_executor.model_loader.sharded_state_loader import (
ShardedStateLoader)
from vllm.model_executor.model_loader.tensorizer_loader import TensorizerLoader
from vllm.model_executor.model_loader.utils import (
get_architecture_class_name, get_model_architecture)
get_architecture_class_name, get_model_architecture, get_model_cls)
def get_model_loader(load_config: LoadConfig) -> BaseModelLoader:
@@ -65,6 +65,7 @@ __all__ = [
"get_model_loader",
"get_architecture_class_name",
"get_model_architecture",
"get_model_cls",
"BaseModelLoader",
"BitsAndBytesModelLoader",
"GGUFModelLoader",
@@ -13,7 +13,7 @@ import time
from collections.abc import Generator
from dataclasses import dataclass
from functools import partial
from typing import Any, BinaryIO, Optional, Union
from typing import TYPE_CHECKING, Any, BinaryIO, Optional, Union
import regex as re
import torch
@@ -24,12 +24,14 @@ from transformers import PretrainedConfig
import vllm.envs as envs
from vllm.config import (ModelConfig, ParallelConfig, VllmConfig,
set_current_vllm_config)
from vllm.engine.arg_utils import EngineArgs
from vllm.logger import init_logger
from vllm.model_executor.layers.vocab_parallel_embedding import (
VocabParallelEmbedding)
from vllm.utils import FlexibleArgumentParser, PlaceholderModule
if TYPE_CHECKING:
from vllm.engine.arg_utils import EngineArgs
try:
from tensorizer import (DecryptionParams, EncryptionParams,
TensorDeserializer, TensorSerializer)
@@ -503,7 +505,7 @@ def serialize_vllm_model(
return model
def tensorize_vllm_model(engine_args: EngineArgs,
def tensorize_vllm_model(engine_args: "EngineArgs",
tensorizer_config: TensorizerConfig,
generate_keyfile: bool = True):
"""Utility to load a model and then serialize it with Tensorizer
@@ -253,6 +253,10 @@ def get_model_architecture(
return model_cls, arch
def get_model_cls(model_config: ModelConfig) -> type[nn.Module]:
return get_model_architecture(model_config)[0]
def get_architecture_class_name(model_config: ModelConfig) -> str:
return get_model_architecture(model_config)[1]