tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add LoRA support (#820)

Browse Source
This commit is contained in:
slaren
2023-04-17 17:28:55 +02:00
committed by GitHub
parent efd05648c8
commit 315a95a4d3
10 changed files with 753 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
llama_util.h
View File

@@ -168,7 +168,7 @@ struct llama_mmap {
#ifdef _POSIX_MAPPED_FILES
static constexpr bool SUPPORTED = true;
llama_mmap(struct llama_file * file) {
llama_mmap(struct llama_file * file, bool prefetch = true) {
size = file->size;
int fd = fileno(file->fp);
int flags = MAP_SHARED;
@@ -180,10 +180,12 @@ struct llama_mmap {
throw format("mmap failed: %s", strerror(errno));
}
// Advise the kernel to preload the mapped memory
if (madvise(addr, file->size, MADV_WILLNEED)) {
fprintf(stderr, "warning: madvise(.., MADV_WILLNEED) failed: %s\n",
strerror(errno));
if (prefetch) {
// Advise the kernel to preload the mapped memory
if (madvise(addr, file->size, MADV_WILLNEED)) {
fprintf(stderr, "warning: madvise(.., MADV_WILLNEED) failed: %s\n",
strerror(errno));
}
}
}
@@ -193,7 +195,7 @@ struct llama_mmap {
#elif defined(_WIN32)
static constexpr bool SUPPORTED = true;
llama_mmap(struct llama_file * file) {
llama_mmap(struct llama_file * file, bool prefetch = true) {
size = file->size;
HANDLE hFile = (HANDLE) _get_osfhandle(_fileno(file->fp));
@@ -215,13 +217,15 @@ struct llama_mmap {
}
#if _WIN32_WINNT >= _WIN32_WINNT_WIN8
// Advise the kernel to preload the mapped memory
WIN32_MEMORY_RANGE_ENTRY range;
range.VirtualAddress = addr;
range.NumberOfBytes = (SIZE_T)size;
if (!PrefetchVirtualMemory(GetCurrentProcess(), 1, &range, 0)) {
fprintf(stderr, "warning: PrefetchVirtualMemory failed: %s\n",
llama_format_win_err(GetLastError()).c_str());
if (prefetch) {
// Advise the kernel to preload the mapped memory
WIN32_MEMORY_RANGE_ENTRY range;
range.VirtualAddress = addr;
range.NumberOfBytes = (SIZE_T)size;
if (!PrefetchVirtualMemory(GetCurrentProcess(), 1, &range, 0)) {
fprintf(stderr, "warning: PrefetchVirtualMemory failed: %s\n",
llama_format_win_err(GetLastError()).c_str());
}
}
#else
#pragma message("warning: You are building for pre-Windows 8; prefetch not supported")