fixup

ggml/include/gguf.h

@@ -77,8 +77,8 @@ extern "C" {
     };
 
     GGML_API struct gguf_context * gguf_init_empty(void);
-    GGML_API struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_params params);
     GGML_API struct gguf_context * gguf_init_from_file_ptr(FILE * file, struct gguf_init_params params);
+    GGML_API struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_params params);
     //GGML_API struct gguf_context * gguf_init_from_buffer(..);
 
     GGML_API void gguf_free(struct gguf_context * ctx);
@@ -190,8 +190,8 @@ extern "C" {
     //
 
     // write the entire context to a binary file
-    GGML_API bool gguf_write_to_file(const struct gguf_context * ctx, const char * fname, bool only_meta);
     GGML_API bool gguf_write_to_file_ptr(const struct gguf_context * ctx, FILE * file, bool only_meta);
+    GGML_API bool gguf_write_to_file(const struct gguf_context * ctx, const char * fname, bool only_meta);
 
     // get the size in bytes of the meta data (header, kv pairs, tensor info) including padding
     GGML_API size_t gguf_get_meta_size(const struct gguf_context * ctx);

ggml/src/gguf.cpp

@@ -1512,6 +1512,19 @@ void gguf_write_to_buf(const struct gguf_context * ctx, std::vector<int8_t> & bu
     gguf_write_out(ctx, gw, only_meta);
 }
 
+bool gguf_write_to_file_ptr(const struct gguf_context * ctx, FILE * file, bool only_meta) {
+    GGML_ASSERT(file);
+
+    try {
+        gguf_writer_file gw(file);
+        gguf_write_out(ctx, gw, only_meta);
+    } catch (const std::runtime_error& ex) {
+        GGML_LOG_ERROR("%s: failed to write GGUF data: %s\n", __func__, ex.what());
+        return false;
+    }
+    return true;
+}
+
 bool gguf_write_to_file(const struct gguf_context * ctx, const char * fname, bool only_meta) {
     FILE * file = ggml_fopen(fname, "wb");
 
@@ -1529,19 +1542,6 @@ bool gguf_write_to_file(const struct gguf_context * ctx, const char * fname, boo
     return success;
 }
 
-bool gguf_write_to_file_ptr(const struct gguf_context * ctx, FILE * file, bool only_meta) {
-    GGML_ASSERT(file);
-
-    try {
-        gguf_writer_file gw(file);
-        gguf_write_out(ctx, gw, only_meta);
-    } catch (const std::runtime_error& ex) {
-        GGML_LOG_ERROR("%s: failed to write GGUF data: %s\n", __func__, ex.what());
-        return false;
-    }
-    return true;
-}
-
 size_t gguf_get_meta_size(const struct gguf_context * ctx) {
     // only return size
     std::vector<int8_t> buf;

src/llama-arch.cpp

@@ -2757,7 +2757,7 @@ std::string LLM_TN_IMPL::str() const {
     if (model_tensors.find(tensor) == model_tensors.end()) {
         const char * name = LLM_TENSOR_NAMES.at(tensor);
         if (suffix != nullptr || bid != -1 || xid != -1) {
-            LLAMA_LOG_ERROR("%s: cannot properly format tensor name %s with suffix=%s bid=%d xid=%d\n",
+            LLAMA_LOG_WARN("%s: cannot properly format tensor name %s with suffix=%s bid=%d xid=%d\n",
                 __func__, name, suffix, bid, xid);
         }
         return name;

src/llama-model.cpp

@@ -7453,7 +7453,6 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
 
         // generic pass: load optional per-tensor/per-expert ".scale" tensors (e.g. NVFP4 scale2)
         // this avoids having to add scale loading to every architecture
-        if (arch != LLM_ARCH_T5) {
         for (int i = 0; i < n_layer; ++i) {
             auto & layer = layers[i];
 
@@ -7523,7 +7522,6 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
             }
         }
     }
-    }
 
     ml.done_getting_tensors();