73 lines
2.2 KiB
Python

from typing import Any, Dict, List
import torch
from vllm.model_executor.quantization_utils.base import QuantizationConfig
class AWQConfig(QuantizationConfig):
"""Config class for AWQ.
Reference: https://arxiv.org/abs/2306.00978
"""
def __init__(
self,
weight_bits: int,
group_size: int,
zero_point: bool,
) -> None:
self.weight_bits = weight_bits
self.group_size = group_size
self.zero_point = zero_point
if self.weight_bits != 4:
raise ValueError(
"Currently, only 4-bit weight quantization is supported for "
f"AWQ, but got {self.weight_bits} bits.")
self.pack_factor = 32 // self.weight_bits
def __repr__(self) -> str:
return (f"AWQConfig(weight_bits={self.weight_bits}, "
f"group_size={self.group_size}, "
f"zero_point={self.zero_point})")
@classmethod
def get_name(cls) -> str:
return "awq"
@classmethod
def get_supported_act_dtypes(cls) -> List[torch.dtype]:
return [torch.half]
@classmethod
def get_min_capability(cls) -> int:
# The AWQ kernel only supports Ampere or newer GPUs.
return 80
@classmethod
def get_config_filenames(cls) -> List[str]:
return [
"quant_config.json", # E.g., casperhansen/vicuna-7b-v1.5-awq
"quantize_config.json", # E.g., abhinavkulkarni/mosaicml-mpt-7b-instruct-w4-g128-awq # pylint: disable=line-too-long
]
@classmethod
def from_config(cls, config: Dict[str, Any]) -> "AWQConfig":
weight_bits = cls.get_from_keys(config, ["w_bit", "bits"])
group_size = cls.get_from_keys(config, ["q_group_size", "group_size"])
zero_point = cls.get_from_keys(config, ["zero_point"])
return cls(weight_bits, group_size, zero_point)
@classmethod
def get_packed_tensor_names(cls) -> List[str]:
return ["qweight", "qzeros"]
@classmethod
def get_transposed_tensor_names(cls) -> List[str]:
return ["qweight", "qzeros", "scales"]
@classmethod
def get_tp_tensor_names(cls) -> List[str]:
return ["qweight", "qzeros", "scales"]