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
@@ -8,6 +8,7 @@ from vllm.distributed import get_tensor_model_parallel_rank, get_tp_group
from vllm.model_executor.layers.fused_moe import FusedMoE, FusedMoEMethodBase
from vllm.model_executor.layers.linear import (LinearBase,
UnquantizedLinearMethod)
from vllm.model_executor.layers.quantization import QuantizationMethods
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.model_executor.utils import set_weight_attrs
@@ -20,7 +21,7 @@ class ExpertsInt8Config(QuantizationConfig):
super().__init__()
@classmethod
def get_name(cls) -> str:
def get_name(cls) -> QuantizationMethods:
return "experts_int8"
@classmethod