Improve configs - ModelConfig (#17130)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -16,6 +16,7 @@ from vllm.model_executor.layers.fused_moe import (FusedMoE, FusedMoEMethodBase,
|
||||
FusedMoeWeightScaleSupported)
|
||||
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 (
|
||||
QuantizationConfig, QuantizeMethodBase)
|
||||
from vllm.model_executor.layers.quantization.kv_cache import BaseKVCacheMethod
|
||||
@@ -83,7 +84,7 @@ class Fp8Config(QuantizationConfig):
|
||||
self.weight_block_size = weight_block_size
|
||||
|
||||
@classmethod
|
||||
def get_name(cls) -> str:
|
||||
def get_name(cls) -> QuantizationMethods:
|
||||
return "fp8"
|
||||
|
||||
@classmethod
|
||||
|
||||
Reference in New Issue
Block a user