mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 22:33:56 +00:00
feat: llama.cpp bump (17f7f4) for SSM performance improvements (#13408)
* 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>
This commit is contained in:
Gabe Goodhart
77
llama/llama.cpp/common/common.cpp
vendored
77
llama/llama.cpp/common/common.cpp
vendored
@@ -694,7 +694,7 @@ bool string_parse_kv_override(const char * data, std::vector<llama_model_kv_over
|
||||
|
||||
// Validate if a filename is safe to use
|
||||
// To validate a full path, split the path by the OS-specific path separator, and validate each part with this function
|
||||
bool fs_validate_filename(const std::string & filename) {
|
||||
bool fs_validate_filename(const std::string & filename, bool allow_subdirs) {
|
||||
if (!filename.length()) {
|
||||
// Empty filename invalid
|
||||
return false;
|
||||
@@ -754,10 +754,14 @@ bool fs_validate_filename(const std::string & filename) {
|
||||
|| (c >= 0xD800 && c <= 0xDFFF) // UTF-16 surrogate pairs
|
||||
|| c == 0xFFFD // Replacement Character (UTF-8)
|
||||
|| c == 0xFEFF // Byte Order Mark (BOM)
|
||||
|| c == '/' || c == '\\' || c == ':' || c == '*' // Illegal characters
|
||||
|| c == ':' || c == '*' // Illegal characters
|
||||
|| c == '?' || c == '"' || c == '<' || c == '>' || c == '|') {
|
||||
return false;
|
||||
}
|
||||
if (!allow_subdirs && (c == '/' || c == '\\')) {
|
||||
// Subdirectories not allowed, reject path separators
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Reject any leading or trailing ' ', or any trailing '.', these are stripped on Windows and will cause a different filename
|
||||
@@ -782,11 +786,29 @@ bool fs_validate_filename(const std::string & filename) {
|
||||
#include <iostream>
|
||||
|
||||
|
||||
#ifdef _WIN32
|
||||
static std::wstring utf8_to_wstring(const std::string & str) {
|
||||
if (str.empty()) {
|
||||
return std::wstring();
|
||||
}
|
||||
|
||||
int size = MultiByteToWideChar(CP_UTF8, 0, str.c_str(), (int)str.size(), NULL, 0);
|
||||
|
||||
if (size <= 0) {
|
||||
return std::wstring();
|
||||
}
|
||||
|
||||
std::wstring wstr(size, 0);
|
||||
MultiByteToWideChar(CP_UTF8, 0, str.c_str(), (int)str.size(), &wstr[0], size);
|
||||
|
||||
return wstr;
|
||||
}
|
||||
#endif
|
||||
|
||||
// returns true if successful, false otherwise
|
||||
bool fs_create_directory_with_parents(const std::string & path) {
|
||||
#ifdef _WIN32
|
||||
std::wstring_convert<std::codecvt_utf8<wchar_t>> converter;
|
||||
std::wstring wpath = converter.from_bytes(path);
|
||||
std::wstring wpath = utf8_to_wstring(path);
|
||||
|
||||
// if the path already exists, check whether it's a directory
|
||||
const DWORD attributes = GetFileAttributesW(wpath.c_str());
|
||||
@@ -859,6 +881,11 @@ bool fs_create_directory_with_parents(const std::string & path) {
|
||||
#endif // _WIN32
|
||||
}
|
||||
|
||||
bool fs_is_directory(const std::string & path) {
|
||||
std::filesystem::path dir(path);
|
||||
return std::filesystem::exists(dir) && std::filesystem::is_directory(dir);
|
||||
}
|
||||
|
||||
std::string fs_get_cache_directory() {
|
||||
std::string cache_directory = "";
|
||||
auto ensure_trailing_slash = [](std::string p) {
|
||||
@@ -893,6 +920,8 @@ std::string fs_get_cache_directory() {
|
||||
cache_directory = std::getenv("HOME") + std::string("/Library/Caches/");
|
||||
#elif defined(_WIN32)
|
||||
cache_directory = std::getenv("LOCALAPPDATA");
|
||||
#elif defined(__EMSCRIPTEN__)
|
||||
GGML_ABORT("not implemented on this platform");
|
||||
#else
|
||||
# error Unknown architecture
|
||||
#endif
|
||||
@@ -912,7 +941,7 @@ std::string fs_get_cache_file(const std::string & filename) {
|
||||
return cache_directory + filename;
|
||||
}
|
||||
|
||||
std::vector<common_file_info> fs_list_files(const std::string & path) {
|
||||
std::vector<common_file_info> fs_list(const std::string & path, bool include_directories) {
|
||||
std::vector<common_file_info> files;
|
||||
if (path.empty()) return files;
|
||||
|
||||
@@ -927,14 +956,22 @@ std::vector<common_file_info> fs_list_files(const std::string & path) {
|
||||
const auto & p = entry.path();
|
||||
if (std::filesystem::is_regular_file(p)) {
|
||||
common_file_info info;
|
||||
info.path = p.string();
|
||||
info.name = p.filename().string();
|
||||
info.path = p.string();
|
||||
info.name = p.filename().string();
|
||||
info.is_dir = false;
|
||||
try {
|
||||
info.size = static_cast<size_t>(std::filesystem::file_size(p));
|
||||
} catch (const std::filesystem::filesystem_error &) {
|
||||
info.size = 0;
|
||||
}
|
||||
files.push_back(std::move(info));
|
||||
} else if (include_directories && std::filesystem::is_directory(p)) {
|
||||
common_file_info info;
|
||||
info.path = p.string();
|
||||
info.name = p.filename().string();
|
||||
info.size = 0; // Directories have no size
|
||||
info.is_dir = true;
|
||||
files.push_back(std::move(info));
|
||||
}
|
||||
} catch (const std::filesystem::filesystem_error &) {
|
||||
// skip entries we cannot inspect
|
||||
@@ -945,6 +982,32 @@ std::vector<common_file_info> fs_list_files(const std::string & path) {
|
||||
return files;
|
||||
}
|
||||
|
||||
//
|
||||
// TTY utils
|
||||
//
|
||||
|
||||
bool tty_can_use_colors() {
|
||||
// Check NO_COLOR environment variable (https://no-color.org/)
|
||||
if (const char * no_color = std::getenv("NO_COLOR")) {
|
||||
if (no_color[0] != '\0') {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Check TERM environment variable
|
||||
if (const char * term = std::getenv("TERM")) {
|
||||
if (std::strcmp(term, "dumb") == 0) {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Check if stdout and stderr are connected to a terminal
|
||||
// We check both because log messages can go to either
|
||||
bool stdout_is_tty = isatty(fileno(stdout));
|
||||
bool stderr_is_tty = isatty(fileno(stderr));
|
||||
|
||||
return stdout_is_tty || stderr_is_tty;
|
||||
}
|
||||
|
||||
//
|
||||
// Model utils
|
||||
|
||||
Reference in New Issue
Block a user