Skip to content

GitLab

Unverified Commit 6b47ef24 authored by Kunshang Ji's avatar Kunshang Ji Committed by GitHub
Browse files

[XPU]Fix `flash_attn_varlen_func` interface on xpu (#22350) 


Signed-off-by: default avatarKunshang Ji <kunshang.ji@intel.com>
parent 1dc8a70b
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
vllm/_ipex_ops.py
View file @ 6b47ef24
...@@ -271,6 +271,7 @@ class ipex_ops: ...@@ -271,6 +271,7 @@ class ipex_ops:
k_descale=None, k_descale=None,
v_descale=None, v_descale=None,
num_splits=0, num_splits=0,
s_aux: Optional[torch.Tensor] = None,
): ):
if cu_seqlens_k is None: if cu_seqlens_k is None:
# cu_seqlens_k is not used in ipex kernel. # cu_seqlens_k is not used in ipex kernel.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment