vllm/vllm/model_executor/model_loader.py
2023-12-12 22:21:45 -08:00

75 lines
3.1 KiB
Python

"""Utilities for selecting and loading models."""
import contextlib
from typing import Type
import torch
import torch.nn as nn
from transformers import PretrainedConfig
from vllm.config import ModelConfig
from vllm.model_executor.models import ModelRegistry
from vllm.model_executor.weight_utils import (get_quant_config,
initialize_dummy_weights)
@contextlib.contextmanager
def _set_default_torch_dtype(dtype: torch.dtype):
"""Sets the default torch dtype to the given dtype."""
old_dtype = torch.get_default_dtype()
torch.set_default_dtype(dtype)
yield
torch.set_default_dtype(old_dtype)
def _get_model_architecture(config: PretrainedConfig) -> Type[nn.Module]:
architectures = getattr(config, "architectures", [])
for arch in architectures:
model_cls = ModelRegistry.load_model_cls(arch)
if model_cls is not None:
return model_cls
raise ValueError(
f"Model architectures {architectures} are not supported for now. "
f"Supported architectures: {ModelRegistry.get_supported_archs()}")
def get_model(model_config: ModelConfig) -> nn.Module:
model_class = _get_model_architecture(model_config.hf_config)
# Get the (maybe quantized) linear method.
linear_method = None
if model_config.quantization is not None:
quant_config = get_quant_config(model_config.quantization,
model_config.model,
model_config.hf_config,
model_config.download_dir)
capability = torch.cuda.get_device_capability()
capability = capability[0] * 10 + capability[1]
if capability < quant_config.get_min_capability():
raise ValueError(
f"The quantization method {model_config.quantization} is not "
"supported for the current GPU. "
f"Minimum capability: {quant_config.get_min_capability()}. "
f"Current capability: {capability}.")
supported_dtypes = quant_config.get_supported_act_dtypes()
if model_config.dtype not in supported_dtypes:
raise ValueError(
f"{model_config.dtype} is not supported for quantization "
f"method {model_config.quantization}. Supported dtypes: "
f"{supported_dtypes}")
linear_method = quant_config.get_linear_method()
with _set_default_torch_dtype(model_config.dtype):
# Create a model instance.
# The weights will be initialized as empty tensors.
with torch.device("cuda"):
model = model_class(model_config.hf_config, linear_method)
if model_config.load_format == "dummy":
# NOTE(woosuk): For accurate performance evaluation, we assign
# random values to the weights.
initialize_dummy_weights(model)
else:
# Load the weights from the cached or downloaded files.
model.load_weights(model_config.model, model_config.download_dir,
model_config.load_format, model_config.revision)
return model.eval()