vulkan: allow proxy collectives without external semaphore FD functions

ggml/src/ggml-backend-impl.h

@@ -83,6 +83,9 @@ extern "C" {
     GGML_API ggml_backend_buffer_t ggml_backend_multi_buffer_alloc_buffer(ggml_backend_buffer_t * buffers, size_t n_buffers);
     GGML_API bool                  ggml_backend_buffer_is_multi_buffer(ggml_backend_buffer_t buffer);
     GGML_API void                  ggml_backend_multi_buffer_set_usage(ggml_backend_buffer_t buffer, enum ggml_backend_buffer_usage usage);
+    // resolve the physical sub-buffer whose memory range contains addr (NULL if none); sub-buffers have a
+    // usable context/get_base, the multi-buffer wrapper does not, so backends need this to find the real buffer
+    GGML_API ggml_backend_buffer_t ggml_backend_multi_buffer_get_buffer(ggml_backend_buffer_t buffer, const void * addr);
 
     //
     // Backend (meta)

ggml/src/ggml-backend-meta.cpp

@@ -1193,10 +1193,24 @@ static enum ggml_status ggml_backend_meta_buffer_init_tensor_impl(ggml_backend_m
         }
         if (t_ij->view_src != nullptr) {
             t_ij->data = (char *) t_ij->view_src->data + t_ij->view_offs;
-        } else if (simple_buf != nullptr) {
+            if (t_ij->view_src->buffer != nullptr) {
+                t_ij->buffer = t_ij->view_src->buffer;
+            }
+        } else if (simple_buf != nullptr && !ggml_backend_buffer_is_multi_buffer(simple_buf)) {
+            // single contiguous buffer: mirror the offset. A multi-buffer has no usable base, so leave the
+            // tensor for the gallocr to place (alloc_ctx_tensors assigns each tensor a real sub-buffer).
             t_ij->data = (char *) ggml_backend_buffer_get_base(simple_buf)
                 + size_t(tensor->data) - size_t(ggml_backend_buffer_get_base(tensor->buffer));
         }
+        // Backends require the physical buffer, not the multi-buffer wrapper (its context is unusable).
+        // Resolve it from the tensor's data address -- works for any tensor, not just views.
+        if (t_ij->buffer != nullptr && t_ij->data != nullptr
+                && ggml_backend_buffer_is_multi_buffer(t_ij->buffer)) {
+            ggml_backend_buffer_t sub = ggml_backend_multi_buffer_get_buffer(t_ij->buffer, t_ij->data);
+            if (sub != nullptr) {
+                t_ij->buffer = sub;
+            }
+        }
         t_ij->extra = tensor->extra;
         for (int i = 0; i < GGML_MAX_SRC; i++) {
             t_ij->src[i] = tensor->src[i];

ggml/src/ggml-backend.cpp

@@ -725,6 +725,20 @@ bool ggml_backend_buffer_is_multi_buffer(ggml_backend_buffer_t buffer) {
     return buffer->iface.free_buffer == ggml_backend_multi_buffer_free_buffer;
 }
 
+ggml_backend_buffer_t ggml_backend_multi_buffer_get_buffer(ggml_backend_buffer_t buffer, const void * addr) {
+    GGML_ASSERT(ggml_backend_buffer_is_multi_buffer(buffer));
+    ggml_backend_multi_buffer_context * ctx = (ggml_backend_multi_buffer_context *) buffer->context;
+    for (size_t i = 0; i < ctx->n_buffers; i++) {
+        ggml_backend_buffer_t sub = ctx->buffers[i];
+        const char * base = (const char *) ggml_backend_buffer_get_base(sub);
+        const size_t size = ggml_backend_buffer_get_size(sub);
+        if ((const char *) addr >= base && (const char *) addr < base + size) {
+            return sub;
+        }
+    }
+    return NULL;
+}
+
 void ggml_backend_multi_buffer_set_usage(ggml_backend_buffer_t buffer, enum ggml_backend_buffer_usage usage) {
     GGML_ASSERT(buffer);
     GGML_ASSERT(ggml_backend_buffer_is_multi_buffer(buffer));