--- a/src/main.cpp
+++ b/src/main.cpp
@@ -16,6 +16,10 @@
 #include <pybind11/numpy.h>
 
 #include "whisper.h"
+#include "ggml-backend.h"
+
+#include <dlfcn.h>
+#include <string>
 
 
 #define STRINGIFY(x) #x
@@ -850,7 +854,25 @@
 
 ////////////
 
+// With GGML_BACKEND_DL the CPU and GPU backends are libraries next to this
+// extension, and whisper.cpp cannot create a context until a CPU device is
+// registered. ggml searches the executable's directory (the interpreter's, for
+// Python) and the working directory, so load them from this module's directory.
+static void load_ggml_backends_beside_module() {
+    Dl_info info;
+    if (dladdr(reinterpret_cast<void *>(&load_ggml_backends_beside_module), &info) == 0 ||
+        info.dli_fname == nullptr) {
+        ggml_backend_load_all();
+        return;
+    }
+    const std::string path(info.dli_fname);
+    const std::size_t slash = path.find_last_of('/');
+    const std::string dir = slash == std::string::npos ? std::string(".") : path.substr(0, slash);
+    ggml_backend_load_all_from_path(dir.c_str());
+}
+
 PYBIND11_MODULE(_pywhispercpp, m) {
+    load_ggml_backends_beside_module();
     m.doc() = R"pbdoc(
         Pywhispercpp: Python binding to whisper.cpp
         -----------------------