server : avoid checkpoint data host copies (#22558)

* server : avoid checkpoint data host copies

* llama : refactor llama_io_read_i

src/llama-io.h

@@ -25,8 +25,8 @@ public:
     llama_io_read_i() = default;
     virtual ~llama_io_read_i() = default;
 
-    virtual const uint8_t * read(size_t size) = 0;
-    virtual void read_to(void * dst, size_t size) = 0;
+    virtual void read(void * dst, size_t size) = 0;
+    virtual void read_tensor(ggml_tensor * tensor, size_t offset, size_t size) = 0;
 
     // bytes read so far
     virtual size_t n_bytes() = 0;