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_flashmla_sparse.py
View File

@@ -5,7 +5,7 @@ import torch
def test_sparse_flashmla_metadata_smoke():
import vllm.attention.ops.flashmla as fm
import vllm.v1.attention.ops.flashmla as fm
ok, reason = fm.is_flashmla_sparse_supported()
if not ok:
@@ -34,7 +34,7 @@ def test_sparse_flashmla_metadata_smoke():
def test_sparse_flashmla_decode_smoke():
import vllm.attention.ops.flashmla as fm
import vllm.v1.attention.ops.flashmla as fm
ok, reason = fm.is_flashmla_sparse_supported()
if not ok:
@@ -97,7 +97,7 @@ def test_sparse_flashmla_decode_smoke():
def test_sparse_flashmla_prefill_smoke():
import vllm.attention.ops.flashmla as fm
import vllm.v1.attention.ops.flashmla as fm
ok, reason = fm.is_flashmla_sparse_supported()
if not ok: