Switch windows build to fully dynamic

Refactor where we store build outputs, and support a fully dynamic loading
model on windows so the base executable has no special dependencies thus
doesn't require a special PATH.

llm/ext_server_windows.go

@@ -0,0 +1,15 @@
+package llm
+
+import (
+	"fmt"
+
+	"github.com/jmorganca/ollama/api"
+)
+
+func newDefaultExtServer(model string, adapters, projectors []string, numLayers int64, opts api.Options) (extServer, error) {
+	// On windows we always load the llama.cpp libraries dynamically to avoid startup DLL dependencies
+	// This ensures we can update the PATH at runtime to get everything loaded
+
+	// Should not happen
+	return nil, fmt.Errorf("no default impl on windows - all dynamic")
+}