Improve configs - ModelConfig (#17130)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-04-30 10:38:22 +08:00
committed by GitHub
parent 2c4f59afc3
commit 13698db634
36 changed files with 490 additions and 648 deletions
@@ -12,6 +12,7 @@ from torch.nn.parameter import Parameter
from vllm import _custom_ops as ops
from vllm.model_executor.layers.linear import LinearBase, LinearMethodBase
from vllm.model_executor.layers.quantization import QuantizationMethods
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig)
from vllm.model_executor.utils import set_weight_attrs
@@ -186,7 +187,7 @@ class AQLMConfig(QuantizationConfig):
f"out_group_size={self.out_group_size})")
@classmethod
def get_name(cls) -> str:
def get_name(cls) -> QuantizationMethods:
return "aqlm"
@classmethod