diff options
Diffstat (limited to 'ggml/src/ggml-cuda.cu')
-rw-r--r-- | ggml/src/ggml-cuda.cu | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu index 73ab0b73..056ca4a4 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -2286,6 +2286,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg case GGML_OP_SOFT_MAX: ggml_cuda_op_soft_max(ctx, dst); break; + case GGML_OP_SOFT_CAP_MAX: + ggml_cuda_op_soft_cap_max(ctx, dst); + break; case GGML_OP_ROPE: ggml_cuda_op_rope(ctx, dst); break; @@ -2876,6 +2879,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons case GGML_OP_CONT: case GGML_OP_DIAG_MASK_INF: case GGML_OP_SOFT_MAX: + case GGML_OP_SOFT_CAP_MAX: return true; case GGML_OP_ROPE: return ggml_is_contiguous(op->src[0]); |