[5/N][Attention] Finish eliminating vllm/attention folder (#32064)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -19,12 +19,12 @@ from compressed_tensors.quantization import (
|
||||
from compressed_tensors.transform import TransformConfig
|
||||
|
||||
import vllm.envs as envs
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.distributed import (
|
||||
get_tensor_model_parallel_rank,
|
||||
get_tensor_model_parallel_world_size,
|
||||
)
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoE
|
||||
from vllm.model_executor.layers.linear import (
|
||||
LinearBase,
|
||||
|
||||
@@ -11,9 +11,9 @@ import vllm.envs as envs
|
||||
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
|
||||
from vllm import _custom_ops as ops
|
||||
from vllm._aiter_ops import rocm_aiter_ops
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.batch_invariant import (
|
||||
vllm_is_batch_invariant,
|
||||
)
|
||||
|
||||
@@ -11,8 +11,8 @@ from torch.nn.parameter import Parameter
|
||||
import vllm.envs as envs
|
||||
import vllm.model_executor.layers.fused_moe.modular_kernel as mk
|
||||
from vllm._custom_ops import cutlass_scaled_fp4_mm, scaled_fp4_quant
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe.config import (
|
||||
FusedMoEConfig,
|
||||
FusedMoEQuantConfig,
|
||||
|
||||
@@ -7,9 +7,9 @@ import torch
|
||||
from torch.nn.parameter import Parameter
|
||||
|
||||
from vllm import envs
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import get_current_vllm_config
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe import (
|
||||
FusedMoE,
|
||||
FusedMoEConfig,
|
||||
|
||||
@@ -8,8 +8,8 @@ import regex as re
|
||||
import torch
|
||||
from torch.nn.parameter import Parameter
|
||||
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.linear import (
|
||||
LinearBase,
|
||||
LinearMethodBase,
|
||||
|
||||
@@ -7,8 +7,8 @@ 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.attention import Attention
|
||||
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 QuantizeMethodBase
|
||||
|
||||
@@ -6,8 +6,8 @@ from typing import TYPE_CHECKING, Any, Optional, cast
|
||||
|
||||
import torch
|
||||
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor.layers.attention import Attention
|
||||
from vllm.model_executor.layers.fused_moe import FusedMoE
|
||||
from vllm.model_executor.layers.linear import (
|
||||
LinearBase,
|
||||
|
||||
Reference in New Issue
Block a user