llama: guard buffer iteration against released device buffers

release_device_weights()/release_device_buffers() leave a null buffer in
ctxs_bufs while the device memory is released for on-demand VRAM sharing.
The memory-breakdown / total_size / clear paths iterated these and called
ggml_backend_buffer_get_size()/get_type()/clear() on the null buffer, tripping
GGML_ASSERT(buffer) and aborting on shutdown of a cold model. Skip null buffers
in llama_model::memory_breakdown and llama_kv_cache::{memory_breakdown,
total_size,clear}.

Assisted-by: Claude

src/llama-kv-cache.cpp

@@ -371,7 +371,9 @@ void llama_kv_cache::clear(bool data) {
 
     if (data) {
         for (auto & [_, buf] : ctxs_bufs) {
-            ggml_backend_buffer_clear(buf.get(), 0);
+            if (buf) { // may be null if evicted for on-demand VRAM sharing
+                ggml_backend_buffer_clear(buf.get(), 0);
+            }
         }
     }
 }
@@ -681,6 +683,9 @@ llama_pos llama_kv_cache::seq_pos_max(llama_seq_id seq_id) const {
 std::map<ggml_backend_buffer_type_t, size_t> llama_kv_cache::memory_breakdown() const {
     std::map<ggml_backend_buffer_type_t, size_t> ret;
     for (const auto & [ctx, buf] : ctxs_bufs) {
+        if (!buf) { // may be null if evicted for on-demand VRAM sharing
+            continue;
+        }
         ggml_backend_buffer_type_t buft = ggml_backend_buffer_get_type(buf.get());
 
         if (hparams.no_alloc) {
@@ -1801,7 +1806,9 @@ size_t llama_kv_cache::total_size() const {
     size_t size = 0;
 
     for (const auto & [_, buf] : ctxs_bufs) {
-        size += ggml_backend_buffer_get_size(buf.get());
+        if (buf) { // may be null if evicted for on-demand VRAM sharing
+            size += ggml_backend_buffer_get_size(buf.get());
+        }
     }
 
     return size;

src/llama-model.cpp

@@ -1832,6 +1832,11 @@ std::map<ggml_backend_buffer_type_t, size_t> llama_model::memory_breakdown() con
             ret[buft] += ggml_backend_alloc_ctx_tensors_from_buft_size(ctx.get(), buft);
         } else {
             for (const auto & buf : bufs) {
+                // buf may be null if the device weights were released for on-demand VRAM sharing
+                // (see release_device_weights); skip it in the breakdown
+                if (!buf) {
+                    continue;
+                }
                 // GGML_ASSERT(ggml_backend_buffer_get_base(buf.get()) != nullptr); // multi_buffer does not have a defined base
                 ret[ggml_backend_buffer_get_type(buf.get())] += ggml_backend_buffer_get_size(buf.get());
             }