fix: handle GPU memory reports and LLM encoding failures (#2020)

This commit is contained in:
leejet authored and GitHub committed 2026-09-22 00:28:52 +08:00
1 parent 97d932b8f8
commit 6dcb5bbd42
4 files changed
+25 -10

No files matched your search

+2 -1
View File
@@ -157,7 +157,8 @@ private:
}
};
CapacityCheck check_capacity(const DeviceMemoryRequest& request,
const std::vector<TensorState*>& states) const;
const std::vector<TensorState*>& states,
bool log_details = false) const;
ggml_backend_buffer_type_t params_buffer_type_for(const TensorState& state) const;
ggml_backend_buffer_type_t split_buffer_type_for(const TensorState& state) const;