Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
ggml: Disable unused pipeline parallelism
Jesse Gross9a43994c45f8
diff --git a/ml/backend/ggml/ggml.go b/ml/backend/ggml/ggml.goindex 680910f8d..7d6831eed 100644--- a/ml/backend/ggml/ggml.go+++ b/ml/backend/ggml/ggml.go@@ -418,7 +418,7 @@ func New(modelPath string, params ml.BackendParams) (ml.Backend, error) {(*C.ggml_backend_buffer_type_t)(unsafe.Pointer(&schedBufts[0])),C.int(len(schedBackends)),C.size_t(maxGraphNodes),- C._Bool(len(gpus) > 1 && slices.Contains(gpus, output.d)),+ C._Bool(false),C._Bool(false),),schedBackends: schedBackends,