llama: fix llama-model-saver (#20503)

* llama : add fd-based model loading via llama_model_load_from_fd

* llama : address review feedback for fd-based model loading

* llama : use FILE pointer instead of fd in public API

* llama : use FILE pointer consistently, address review feedback

* fixup

* fix tensor names

* fix llama-model-saver

* roundtrip tests

* fixup

* refactor tests

* fix prints

* fix model saving

* fix CI, disable Chameleon

* print seed

---------

Co-authored-by: Siddhesh2377 <siddheshsonar2377@gmail.com>

src/llama-mmap.cpp

@@ -86,6 +86,14 @@ struct llama_file::impl {
         seek(0, SEEK_SET);
     }
 
+    impl(FILE * file) : owns_fp(false) {
+        fp = file;
+        fp_win32 = (HANDLE) _get_osfhandle(_fileno(fp));
+        seek(0, SEEK_END);
+        size = tell();
+        seek(0, SEEK_SET);
+    }
+
     size_t tell() const {
         LARGE_INTEGER li;
         li.QuadPart = 0;
@@ -159,7 +167,7 @@ struct llama_file::impl {
     }
 
     ~impl() {
-        if (fp) {
+        if (fp && owns_fp) {
             std::fclose(fp);
         }
     }
@@ -209,6 +217,13 @@ struct llama_file::impl {
         seek(0, SEEK_SET);
     }
 
+    impl(FILE * file) : fname("(file*)"), owns_fp(false) {
+        fp = file;
+        seek(0, SEEK_END);
+        size = tell();
+        seek(0, SEEK_SET);
+    }
+
     size_t tell() const {
         if (fd == -1) {
             long ret = std::ftell(fp);
@@ -353,7 +368,7 @@ struct llama_file::impl {
     ~impl() {
         if (fd != -1) {
             close(fd);
-        } else {
+        } else if (owns_fp) {
             std::fclose(fp);
         }
     }
@@ -369,10 +384,14 @@ struct llama_file::impl {
 
     FILE * fp{};
     size_t size{};
+    bool owns_fp = true;
 };
 
 llama_file::llama_file(const char * fname, const char * mode, const bool use_direct_io) :
     pimpl(std::make_unique<impl>(fname, mode, use_direct_io)) {}
+
+llama_file::llama_file(FILE * file) : pimpl(std::make_unique<impl>(file)) {}
+
 llama_file::~llama_file() = default;
 
 size_t llama_file::tell() const { return pimpl->tell(); }