Improve configs - ModelConfig (#17130)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -8,6 +8,7 @@ import torch
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoE
|
||||
from vllm.model_executor.layers.linear import (LinearBase, LinearMethodBase,
|
||||
UnquantizedLinearMethod)
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
from vllm.model_executor.layers.quantization.base_config import ( # noqa: E501
|
||||
QuantizationConfig, QuantizeMethodBase)
|
||||
from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
|
||||
@@ -47,7 +48,7 @@ class QuarkConfig(QuantizationConfig):
|
||||
def get_min_capability(cls) -> int:
|
||||
return 70
|
||||
|
||||
def get_name(self) -> str:
|
||||
def get_name(self) -> QuantizationMethods:
|
||||
return "quark"
|
||||
|
||||
def get_quant_method(self, layer: torch.nn.Module,
|
||||
|
||||
Reference in New Issue
Block a user