cont : cleanup

common/debug.cpp

@@ -47,7 +47,7 @@ static float common_ggml_get_float_value(const uint8_t * data,
 
 #define INDENT "    "
 
-void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n, bool abort_on_nan) {
+static void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n, bool abort_on_nan) {
     GGML_ASSERT(n > 0);
     float sum = 0;
     for (int64_t i3 = 0; i3 < ne[3]; i3++) {
@@ -112,7 +112,7 @@ void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * n
  * @return true to receive data or continue the graph, false otherwise
  */
 bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data) {
-    auto * cb_data = (base_callback_data *) user_data;
+    auto * cb_data = (common_debug_cb_user_data *) user_data;
 
     const struct ggml_tensor * src0 = t->src[0];
     const struct ggml_tensor * src1 = t->src[1];

common/debug.h

@@ -6,32 +6,23 @@
 
 // common debug functions and structs
 
-// Print a tensor's detailed data
-// data - the tensor's data in byte format
-// type - the tensor's quantization type
-// ne   - the tensor dimensions array
-// nb   - the tensor strides array
-// n    - the number of rows/columns to fully print
-// aon  - abort if NaN is encountered
-void common_debug_print_tensor(uint8_t * data, ggml_type type, const int64_t * ne, const size_t * nb, int64_t n, bool aon = false);
-
 // Intended to use as callback for ggml_backend_sched_eval_callback
 // prints tensors that are processed in the computation graph
-// by default prints all tensors, but can be configured by creating a `base_callback_data` instance with
+// by default prints all tensors, but can be configured by creating a `common_debug_cb_user_data` instance with
 // non-empty filter_patterns. See examples/debug.ccp for possible usage patterns
-// `base_callback_data` contains `abort_on_nan` flag that determines whether an error should be thrown whenever a NaN is encountered
+// `common_debug_cb_user_data` contains `abort_on_nan` flag that determines whether an error should be thrown whenever a NaN is encountered
 // in a tensor (useful for stopping debug sessions on first erroneous tensor)
 // The callback data will be passed as the third parameter (user_data)
 bool common_debug_cb_eval(struct ggml_tensor * t, bool ask, void * user_data);
 
-struct base_callback_data {
+struct common_debug_cb_user_data {
     std::vector<uint8_t>    data;
     std::vector<std::regex> tensor_filters;
     bool                    abort_on_nan{false};
 
-    base_callback_data() = default;
+    common_debug_cb_user_data() = default;
 
-    base_callback_data(common_params & params, const std::vector<std::string> & filter_patterns, bool abort_on_nan = false) {
+    common_debug_cb_user_data(common_params & params, const std::vector<std::string> & filter_patterns, bool abort_on_nan = false) {
         for (const auto & pattern : filter_patterns) {
             try {
                 std::string anchored_pattern = "^" + pattern;

examples/debug/debug.cpp

@@ -202,10 +202,14 @@ static bool run(llama_context * ctx, const common_params & params) {
     print_tokenized_prompt(ctx, tokens, params.prompt);
 
     if (params.save_logits) {
-        output_data output {ctx, model, params};
-        std::filesystem::path model_path{params.model.path};
-        std::string model_name{model_path.stem().string()};
-        save_output_data(output, model_name, params.logits_output_dir);
+        try {
+            output_data output {ctx, model, params};
+            std::filesystem::path model_path{params.model.path};
+            std::string model_name{model_path.stem().string()};
+            save_output_data(output, model_name, params.logits_output_dir);
+        } catch (const std::exception & e) {
+            LOG_ERR("%s : error saving logits: %s\n", __func__, e.what());
+        }
     }
 
     return true;
@@ -223,7 +227,7 @@ int main(int argc, char ** argv) {
     llama_backend_init();
     llama_numa_init(params.numa);
 
-    std::optional<base_callback_data> cb_data;
+    std::optional<common_debug_cb_user_data> cb_data;
     if (!params.save_logits) {
         cb_data.emplace(params, params.tensor_filter);
     }

examples/eval-callback/eval-callback.cpp

@@ -3,7 +3,6 @@
 #include "debug.h"
 #include "log.h"
 #include "llama.h"
-#include "llama-cpp.h"
 
 #include <clocale>
 #include <string>
@@ -38,7 +37,7 @@ static bool run(llama_context * ctx, const common_params & params) {
 int main(int argc, char ** argv) {
     std::setlocale(LC_NUMERIC, "C");
 
-    base_callback_data cb_data;
+    common_debug_cb_user_data cb_data;
 
     common_params params;
 

tools/mtmd/debug/mtmd-debug.cpp

@@ -72,7 +72,7 @@ int main(int argc, char ** argv) {
 
     mtmd::context_ptr ctx_mtmd;
     common_init_result_ptr llama_init;
-    base_callback_data cb_data;
+    common_debug_cb_user_data cb_data;
 
     llama_init = common_init_from_params(params);
     {

tools/mtmd/mtmd-cli.cpp

@@ -90,7 +90,7 @@ struct mtmd_cli_context {
     int n_threads    = 1;
     llama_pos n_past = 0;
 
-    base_callback_data cb_data;
+    common_debug_cb_user_data cb_data;
 
     mtmd_cli_context(common_params & params) : llama_init(common_init_from_params(params)) {
         model = llama_init->model();