|
|
@@ -286,9 +286,6 @@ void ggml_cuda_flash_attn_ext_tile_f32(ggml_backend_cuda_context & ctx, ggml_ten
|
|
|
const ggml_tensor * KQV = dst;
|
|
|
const ggml_tensor * Q = dst->src[0];
|
|
|
|
|
|
- const int32_t precision = KQV->op_params[2];
|
|
|
- GGML_ASSERT(precision == GGML_PREC_DEFAULT);
|
|
|
-
|
|
|
if (Q->ne[1] <= 16) {
|
|
|
constexpr int cols_per_block = 16;
|
|
|
constexpr int parallel_blocks = 4;
|