fix: detect allocation failures as out-of-memory errors (#6459)

The Llama.cpp backend can emit the phrase “failed to allocate” when it runs out of memory.
Adding this check ensures such messages are correctly classified as out‑of‑memory errors,
providing more accurate error handling CPU backends.

src-tauri/plugins/tauri-plugin-llamacpp/src/error.rs

@@ -48,6 +48,7 @@ impl LlamacppError {
         let lower_stderr = stderr.to_lowercase();
         // TODO: add others
         let is_out_of_memory = lower_stderr.contains("out of memory")
+            || lower_stderr.contains("failed to allocate")
             || lower_stderr.contains("insufficient memory")
             || lower_stderr.contains("erroroutofdevicememory") // vulkan specific
             || lower_stderr.contains("kiogpucommandbuffercallbackerroroutofmemory") // Metal-specific error code