mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 22:33:56 +00:00
b95693056c
* feat: Bump llama.cpp to the latest master (17f7f4b) This brings in significant improvements to prefill performance for all models using the SSM_CONV and SSM_SCAN ops (granite4, jamba, falcon-h, nemotron-h, Qwen3 Next) on Apple Metal. See https://github.com/ggml-org/llama.cpp/pull/17876 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 1-4 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Update patches 5-12 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 13-18 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patch 20 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 21-31 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Sync vendored code The two files I'm not sure about here are the swap from gemma3-iswa.cpp to gemma3.cpp (I chose to include this because I think it's required), and the inclusion of `ggml-zendnn.h` which I chose to omit. Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
78 lines
2.5 KiB
Diff
78 lines
2.5 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: jmorganca <jmorganca@gmail.com>
|
|
Date: Tue, 8 Apr 2025 15:34:37 -0700
|
|
Subject: [PATCH] clip-unicode
|
|
|
|
fixes loading vision models in llama.cpp on windows
|
|
filesystems for paths that include wide characters
|
|
---
|
|
tools/mtmd/clip.cpp | 39 +++++++++++++++++++++++++++++++++++++++
|
|
1 file changed, 39 insertions(+)
|
|
|
|
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
|
|
index 3ed08a0fe..6be1470ad 100644
|
|
--- a/tools/mtmd/clip.cpp
|
|
+++ b/tools/mtmd/clip.cpp
|
|
@@ -24,6 +24,19 @@
|
|
#include <array>
|
|
#include <functional>
|
|
|
|
+#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
|
|
+
|
|
struct clip_logger_state g_logger_state = {clip_log_callback_default, NULL};
|
|
|
|
enum ffn_op_type {
|
|
@@ -3257,7 +3270,29 @@ struct clip_model_loader {
|
|
{
|
|
std::vector<uint8_t> read_buf;
|
|
|
|
+#ifdef _WIN32
|
|
+ int wlen = MultiByteToWideChar(CP_UTF8, 0, fname.c_str(), -1, NULL, 0);
|
|
+ if (!wlen) {
|
|
+ throw std::runtime_error(string_format("%s: failed to convert filename to wide string\n", __func__));
|
|
+ }
|
|
+ wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t));
|
|
+ wlen = MultiByteToWideChar(CP_UTF8, 0, fname.c_str(), -1, wbuf, wlen);
|
|
+ if (!wlen) {
|
|
+ free(wbuf);
|
|
+ throw std::runtime_error(string_format("%s: failed to convert filename to wide string\n", __func__));
|
|
+ }
|
|
+#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) {
|
|
throw std::runtime_error(string_format("%s: failed to open %s\n", __func__, fname.c_str()));
|
|
}
|
|
@@ -3284,7 +3319,11 @@ struct clip_model_loader {
|
|
ggml_backend_tensor_set(cur, read_buf.data(), 0, num_bytes);
|
|
}
|
|
}
|
|
+#if defined(_WIN32) && defined(__GLIBCXX__)
|
|
+ close(fd);
|
|
+#else
|
|
fin.close();
|
|
+#endif
|
|
|
|
LOG_DBG("%s: loaded %zu tensors from %s\n", __func__, tensors_to_load.size(), fname.c_str());
|
|
}
|