Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions ds4_cuda.cu
Original file line number Diff line number Diff line change
Expand Up @@ -6168,7 +6168,7 @@ extern "C" int ds4_gpu_attention_prefill_raw_heads_tensor(ds4_gpu_tensor *heads,
if (!tmp) return 0;
float *scores = tmp;
float *out_tmp = (float *)((char *)tmp + out_offset);
const float alpha = rsqrtf((float)head_dim);
const float alpha = 1.0f/sqrtf((float)head_dim);
const float beta = 0.0f;
cublasStatus_t st = cublasSgemmStridedBatched(g_cublas,
CUBLAS_OP_T,
Expand Down Expand Up @@ -6538,7 +6538,7 @@ static int attention_prefill_mixed_launch(
n_comp,
head_dim);
if (!cuda_ok(cudaGetLastError(), "attention mixed kv pack launch")) return 0;
const float alpha = rsqrtf((float)head_dim);
const float alpha = 1.0f/sqrtf((float)head_dim);
const float beta = 0.0f;
cublasStatus_t st = cublasSgemmStridedBatched(g_cublas,
CUBLAS_OP_T,
Expand Down