biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

Browse Source 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
This commit is contained in:
Matthew Bonanni
2026-01-27 10:02:51 -05:00
committed by GitHub
parent 1f3a2c2944
commit a608b4c6c2
151 changed files with 585 additions and 527 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
vllm/model_executor/models/openpangu.py
View File

@@ -29,7 +29,6 @@ import torch
from torch import nn
from transformers import PretrainedConfig
from vllm.attention.layer import Attention, AttentionType
from vllm.compilation.decorators import support_torch_compile
from vllm.config import CacheConfig, ParallelConfig, VllmConfig
from vllm.distributed import (
@@ -41,7 +40,8 @@ from vllm.distributed import (
tensor_model_parallel_all_gather,
)
from vllm.model_executor.layers.activation import SiluAndMul
from vllm.model_executor.layers.attention.static_sink_attention import (
from vllm.model_executor.layers.attention import (
Attention,
StaticSinkAttention,
)
from vllm.model_executor.layers.fused_moe import SharedFusedMoE
@@ -84,6 +84,7 @@ from vllm.model_executor.utils import set_weight_attrs
from vllm.platforms import current_platform
from vllm.sequence import IntermediateTensors
from vllm.transformers_utils.config import set_default_rope_theta
from vllm.v1.attention.backend import AttentionType
from vllm.v1.attention.backends.flash_attn_diffkv import FlashAttentionDiffKVBackend