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 056ca4a4..cf053559 100644 --- a/ggml/src/ggml-cuda.cu +++ b/ggml/src/ggml-cuda.cu @@ -2248,6 +2248,9 @@ static bool ggml_cuda_compute_forward(ggml_backend_cuda_context & ctx, struct gg case GGML_OP_RMS_NORM: ggml_cuda_op_rms_norm(ctx, dst); break; + case GGML_OP_FUSED_RMS_NORM: + ggml_cuda_op_fused_rms_norm(ctx, dst); + break; case GGML_OP_MUL_MAT: if (dst->src[0]->ne[3] != dst->src[1]->ne[3]) { GGML_CUDA_LOG_ERROR("%s: cannot compute %s: src0->ne[3] = %" PRId64 ", src1->ne[3] = %" PRId64 " - fallback to CPU\n", __func__, dst->name, dst->src[0]->ne[3], dst->src[1]->ne[3]); @@ -2871,6 +2874,7 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons case GGML_OP_MUL: case GGML_OP_DIV: case GGML_OP_RMS_NORM: + case GGML_OP_FUSED_RMS_NORM: case GGML_OP_SCALE: case GGML_OP_SOFTCAP: case GGML_OP_SQR: |