diff options
Diffstat (limited to 'ggml-cuda/softmax.cu')
| -rw-r--r-- | ggml-cuda/softmax.cu | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-cuda/softmax.cu b/ggml-cuda/softmax.cu index ce64f2f2..c24abae1 100644 --- a/ggml-cuda/softmax.cu +++ b/ggml-cuda/softmax.cu @@ -130,6 +130,7 @@ static void soft_max_f32_cuda(const float * x, const T * mask, float * dst, cons const float m0 = powf(2.0f, -(max_bias ) / n_head_log2); const float m1 = powf(2.0f, -(max_bias / 2.0f) / n_head_log2); + // FIXME: this limit could be raised by ~2-4x on Ampere or newer if (shmem < ggml_cuda_info().devices[ggml_cuda_get_device()].smpb) { switch (ncols_x) { case 32: |