minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

[Intel GPU] import flash_attn functions from sgl_kernel only (#22438)

Browse Source
This commit is contained in:
Polisetty V R K Jyothendra Varma
2026-04-10 15:10:00 +08:00
committed by GitHub
parent 5ba7d4e523
commit 599cce4d82
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/layers/attention/xpu_backend.py
+1 -5
View File
@@ -20,11 +20,7 @@ if TYPE_CHECKING:
from sglang.srt.model_executor.model_runner import ModelRunner from sglang.srt.model_executor.model_runner import ModelRunner
from sgl_kernel import merge_state_v2 from sgl_kernel import merge_state_v2
from sgl_kernel.flash_attn import flash_attn_varlen_func, flash_attn_with_kvcache
from sglang.jit_kernel.flash_attention import (
flash_attn_varlen_func,
flash_attn_with_kvcache,
)
class XPUAttentionBackend(AttentionBackend): class XPUAttentionBackend(AttentionBackend):