[Attention] Update attention imports (#29540)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -7,6 +7,7 @@ import torch
|
||||
from torch.nn.parameter import Parameter
|
||||
|
||||
from vllm import _custom_ops as ops
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.linear import LinearBase, UnquantizedLinearMethod
|
||||
from vllm.model_executor.layers.quantization import QuantizationMethods
|
||||
@@ -65,8 +66,6 @@ class PTPCFp8Config(Fp8Config):
|
||||
def get_quant_method(
|
||||
self, layer: torch.nn.Module, prefix: str
|
||||
) -> Optional["QuantizeMethodBase"]:
|
||||
from vllm.attention.layer import Attention # Avoid circular import
|
||||
|
||||
if isinstance(layer, LinearBase):
|
||||
if is_layer_skipped(prefix, self.ignored_layers):
|
||||
return UnquantizedLinearMethod()
|
||||
|
||||
Reference in New Issue
Block a user