[Attention] Remove imports from vllm/attention/__init__.py (#29342)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
@@ -9,7 +9,8 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -32,7 +32,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import ApertusConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.layers.encoder_only_attention import EncoderOnlyAttention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
|
||||
@@ -8,7 +8,7 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -29,7 +29,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch.nn.functional as F
|
||||
from torch import nn
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -27,7 +27,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import BloomConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -16,7 +16,7 @@ from transformers import (
|
||||
ChameleonVQVAEConfig,
|
||||
)
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.config.multimodal import BaseDummyOptions
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -12,7 +12,7 @@ import torch
|
||||
from torch import nn
|
||||
from torch.nn import LayerNorm
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -14,8 +14,7 @@ from transformers import (
|
||||
CLIPVisionConfig,
|
||||
)
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import MultiHeadAttention
|
||||
from vllm.attention.layer import Attention, MultiHeadAttention
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.config.multimodal import BaseDummyOptions
|
||||
from vllm.distributed import divide, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -30,7 +30,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Cohere2Config, CohereConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -8,7 +8,7 @@ import torch
|
||||
import torch.nn as nn
|
||||
from transformers import DbrxConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
get_pp_group,
|
||||
|
||||
@@ -33,8 +33,8 @@ from torch import nn
|
||||
from transformers import DeepseekV2Config, DeepseekV3Config
|
||||
|
||||
from vllm._aiter_ops import rocm_aiter_ops
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.backends.abstract import AttentionBackend
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.ops.common import pack_seq_triton, unpack_seq_triton
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ParallelConfig, VllmConfig, get_current_vllm_config
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Dots1Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
|
||||
# from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -28,7 +28,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Exaone4Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -30,7 +30,7 @@ from torch import nn
|
||||
from torch.nn import LayerNorm
|
||||
from transformers import FalconConfig as HF_FalconConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -26,7 +26,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GemmaConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -23,7 +23,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Gemma2Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -23,7 +23,8 @@ import torch.nn.functional as F
|
||||
from torch import nn
|
||||
from transformers import Gemma3TextConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -21,7 +21,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers.models.gemma3n.configuration_gemma3n import Gemma3nTextConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -29,7 +29,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Glm4Config
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers.models.glm4_moe import Glm4MoeConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -27,7 +27,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GPT2Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed.parallel_state import (
|
||||
|
||||
@@ -28,7 +28,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GPTBigCodeConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -26,7 +26,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GPTJConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -26,7 +26,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GPTNeoXConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -7,7 +7,8 @@ import torch.distributed as dist
|
||||
from torch import nn
|
||||
from transformers import GptOssConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import GraniteConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -31,7 +31,7 @@ from typing import Any
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
import torch.nn.functional as F
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -33,7 +33,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -10,7 +10,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -28,7 +28,7 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -7,7 +7,7 @@ import torch
|
||||
import torch.nn as nn
|
||||
from transformers import Lfm2Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -6,7 +6,7 @@ from itertools import islice
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -31,7 +31,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import LlamaConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.layers.encoder_only_attention import EncoderOnlyAttention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
|
||||
@@ -24,7 +24,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Llama4TextConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.layers.chunked_local_attention import ChunkedLocalAttention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
|
||||
@@ -33,7 +33,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -29,7 +29,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
from vllm.model_executor.layers.layernorm import RMSNorm
|
||||
|
||||
@@ -30,7 +30,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -14,7 +14,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import MiniMaxConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionMetadata
|
||||
from vllm.attention.backends.abstract import AttentionMetadata
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig
|
||||
from vllm.distributed.parallel_state import (
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import MixtralConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -17,8 +17,7 @@ from transformers import BatchFeature, PretrainedConfig, ProcessorMixin, TensorT
|
||||
from transformers.image_utils import ImageInput
|
||||
from transformers.tokenization_utils_base import TextInput
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import MultiHeadAttention
|
||||
from vllm.attention.layer import Attention, MultiHeadAttention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.config.multimodal import BaseDummyOptions
|
||||
|
||||
@@ -10,7 +10,7 @@ import torch
|
||||
import torch.nn as nn
|
||||
from transformers import MptConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -30,7 +30,7 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import LlamaConfig
|
||||
|
||||
from vllm.attention import AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import OlmoConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -32,7 +32,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Olmo2Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -21,7 +21,7 @@ from itertools import islice
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -29,7 +29,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ParallelConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -27,7 +27,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import OPTConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -15,7 +15,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -33,7 +33,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -30,7 +30,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PersimmonConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -45,7 +45,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PhiConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -31,7 +31,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers.configuration_utils import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -16,7 +16,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -33,7 +33,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Qwen2Config
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.layers.encoder_only_attention import EncoderOnlyAttention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
|
||||
@@ -34,7 +34,7 @@ import torch.nn.functional as F
|
||||
from torch import nn
|
||||
from transformers import Qwen2MoeConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -30,7 +30,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Qwen3Config
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -31,7 +31,7 @@ from typing import Any
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig, get_current_vllm_config
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -10,7 +10,8 @@ from einops import rearrange
|
||||
from torch import nn
|
||||
from transformers.activations import ACT2FN
|
||||
|
||||
from vllm.attention import Attention, AttentionMetadata
|
||||
from vllm.attention.backends.abstract import AttentionMetadata
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import (
|
||||
CacheConfig,
|
||||
|
||||
@@ -30,7 +30,8 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig as SeedOssConfig
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -30,7 +30,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import PretrainedConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -29,7 +29,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import StableLmConfig
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
from vllm.model_executor.layers.activation import SiluAndMul
|
||||
|
||||
@@ -28,7 +28,7 @@ import torch
|
||||
from torch import nn
|
||||
from transformers import Starcoder2Config
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, VllmConfig
|
||||
from vllm.distributed import get_pp_group, get_tensor_model_parallel_world_size
|
||||
|
||||
@@ -9,7 +9,7 @@ from typing import Any
|
||||
import torch
|
||||
from torch import nn
|
||||
|
||||
from vllm.attention import Attention
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.compilation.decorators import support_torch_compile
|
||||
from vllm.config import CacheConfig, ModelConfig, VllmConfig
|
||||
from vllm.distributed import (
|
||||
|
||||
@@ -27,7 +27,8 @@ from torch import nn
|
||||
from transformers import AutoModel
|
||||
from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention
|
||||
from vllm.attention.layers.encoder_only_attention import EncoderOnlyAttention
|
||||
from vllm.config.utils import getattr_iter
|
||||
from vllm.distributed import get_pp_group, get_tp_group
|
||||
|
||||
@@ -16,8 +16,8 @@ from transformers import (
|
||||
)
|
||||
from transformers.models.whisper.modeling_whisper import sinusoids
|
||||
|
||||
from vllm.attention import Attention, AttentionType
|
||||
from vllm.attention.layer import MultiHeadAttention
|
||||
from vllm.attention.backends.abstract import AttentionType
|
||||
from vllm.attention.layer import Attention, MultiHeadAttention
|
||||
from vllm.attention.layers.cross_attention import CrossAttention
|
||||
from vllm.config import CacheConfig, ModelConfig, SpeechToTextConfig, VllmConfig
|
||||
from vllm.config.multimodal import BaseDummyOptions
|
||||
|
||||
Reference in New Issue
Block a user