[1/N][Attention] Restructure attention: move files (#31916)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-09 16:10:24 -05:00
committed by GitHub
parent 1f8b7c536b
commit 2612ba9285
195 changed files with 426 additions and 396 deletions

View File

@@ -25,7 +25,6 @@ from torch import nn
from transformers import Llama4TextConfig
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
from vllm.distributed import (
@@ -34,6 +33,9 @@ from vllm.distributed import (
tensor_model_parallel_all_gather,
)
from vllm.logger import init_logger
from vllm.model_executor.layers.attention.chunked_local_attention import (
ChunkedLocalAttention,
)
from vllm.model_executor.layers.fused_moe import SharedFusedMoE
from vllm.model_executor.layers.layernorm import RMSNorm
from vllm.model_executor.layers.linear import (