ollama/llama/patches/0006-clip-unicode.patch
Daniel Hiltgen bf4018b9ec
llama: Decouple patching script from submodule (#7139)
* Refine llama.cpp vendoring workflow tools

Switch from the sync.sh over to make based tooling

* Run new make sync and patch flow
2024-10-17 15:03:09 -07:00

76 lines
2.2 KiB
Diff

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me>
Date: Mon, 16 Sep 2024 15:53:15 -0700
Subject: [PATCH] clip-unicode
---
examples/llava/clip.cpp | 40 +++++++++++++++++++++++++++++++++++++++-
1 file changed, 39 insertions(+), 1 deletion(-)
diff --git a/examples/llava/clip.cpp b/examples/llava/clip.cpp
index 14e02c8d..6e849d8e 100644
--- a/examples/llava/clip.cpp
+++ b/examples/llava/clip.cpp
@@ -44,6 +44,19 @@
#define LOG_ERR(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
#define LOG_DBG(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
+#if defined(_WIN32)
+#define WIN32_LEAN_AND_MEAN
+#ifndef NOMINMAX
+ #define NOMINMAX
+#endif
+#include <windows.h>
+#if __GLIBCXX__
+#include <cstdio>
+#include <ext/stdio_filebuf.h>
+#include <fcntl.h>
+#endif
+#endif
+
//#define CLIP_DEBUG_FUNCTIONS
// RGB uint8 image
@@ -1225,8 +1238,29 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
gguf_free(ctx);
return nullptr;
}
-
+#ifdef _WIN32
+ int wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, NULL, 0);
+ if (!wlen) {
+ return NULL;
+ }
+ wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
+ wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, wbuf, wlen);
+ if (!wlen) {
+ free(wbuf);
+ return NULL;
+ }
+#if __GLIBCXX__
+ int fd = _wopen(wbuf, _O_RDONLY | _O_BINARY);
+ __gnu_cxx::stdio_filebuf<char> buffer(fd, std::ios_base::in);
+ std::istream fin(&buffer);
+#else // MSVC
+ // unused in our current build
+ auto fin = std::ifstream(wbuf, std::ios::binary);
+#endif
+ free(wbuf);
+#else
auto fin = std::ifstream(fname, std::ios::binary);
+#endif
if (!fin) {
LOG_ERR("cannot open model file for loading tensors\n");
clip_free(new_clip);
@@ -1266,7 +1300,11 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) {
ggml_backend_tensor_set(cur, read_buf.data(), 0, num_bytes);
}
}
+#if defined(_WIN32) && defined(__GLIBCXX__)
+ close(fd);
+#else
fin.close();
+#endif
}
// vision model