wip: next ollama runner

implement llama and mllama model architectures in go using ggml (through
cgo)

ml/nn/convolution.go

@@ -0,0 +1,11 @@
+package nn
+
+import "github.com/ollama/ollama/ml"
+
+type Conv2D struct {
+	Weight ml.Tensor `ggml:"weight"`
+}
+
+func (m *Conv2D) Forward(ctx ml.Context, t ml.Tensor, s0, s1, p0, p1, d0, d1 int) ml.Tensor {
+	return m.Weight.Conv2D(ctx, t, s0, s1, p0, p1, d0, d1)
+}