Skip to content

Commit 42d912f

Browse files
committed
fix build error
1 parent 49483bc commit 42d912f

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

onnxruntime/contrib_ops/webgpu/bert/group_query_attention.cc

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -207,7 +207,9 @@ Status GroupQueryAttention::ComputeInternal(onnxruntime::webgpu::ComputeContext&
207207
seqlen_k,
208208
total_seqlen_tensor,
209209
scale_,
210-
softcap_));
210+
softcap_,
211+
0,
212+
context.DeviceLimits().maxComputeInvocationsPerWorkgroup));
211213
params.use_smooth_softmax = use_smooth_softmax_;
212214
params.rotary_interleaved = rotary_interleaved_;
213215

0 commit comments

Comments
 (0)