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

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/kernels/attention/test_attention_selector.py
View File

@@ -6,13 +6,13 @@ from unittest.mock import patch
import pytest
import torch
from vllm.attention.backends.registry import AttentionBackendEnum
from vllm.attention.selector import _cached_get_attn_backend, get_attn_backend
from vllm.config import AttentionConfig, VllmConfig, set_current_vllm_config
from vllm.platforms import current_platform
from vllm.platforms.cpu import CpuPlatform
from vllm.platforms.cuda import CudaPlatform
from vllm.platforms.rocm import RocmPlatform
from vllm.v1.attention.backends.registry import AttentionBackendEnum
from vllm.v1.attention.selector import _cached_get_attn_backend, get_attn_backend
@pytest.fixture(autouse=True)
@@ -182,7 +182,7 @@ def test_backend_selection(
expected = name
assert backend.get_name() == expected
elif name == "FLASH_ATTN_MLA":
from vllm.attention.utils.fa_utils import (
from vllm.v1.attention.backends.fa_utils import (
flash_attn_supports_mla,
)