vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-11 13:11:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

up to date merge, without vulkan-gen-shaders. They will be built before each release from now on, as they are very large

Browse source
This commit is contained in:
Concedo 2024-12-13 17:18:01 +08:00
commit ed75f8a741
24 changed files with 655 additions and 573 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/llama.cpp
View file

@ -1808,7 +1808,7 @@ private:
DWORD bufLen = FormatMessageA(FORMAT_MESSAGE_ALLOCATE_BUFFER | FORMAT_MESSAGE_FROM_SYSTEM | FORMAT_MESSAGE_IGNORE_INSERTS,
NULL, error_code, MAKELANGID(LANG_NEUTRAL, SUBLANG_DEFAULT), (LPSTR)&lpMsgBuf, 0, NULL);
if (!bufLen) {
ret = format("Win32 error code: %s", error_code);
ret = format("Win32 error code: %lx", error_code);
} else {
ret = lpMsgBuf;
LocalFree(lpMsgBuf);
@ -2147,7 +2147,7 @@ struct llama_mmap {
HMODULE hKernel32 = GetModuleHandleW(L"kernel32.dll");
// may fail on pre-Windows 8 systems
pPrefetchVirtualMemory = reinterpret_cast<decltype(pPrefetchVirtualMemory)> (GetProcAddress(hKernel32, "PrefetchVirtualMemory"));
pPrefetchVirtualMemory = (decltype(pPrefetchVirtualMemory))(void *) GetProcAddress(hKernel32, "PrefetchVirtualMemory");
if (pPrefetchVirtualMemory) {
// advise the kernel to preload the mapped memory
@ -21755,7 +21755,7 @@ float * llama_get_embeddings_ith(struct llama_context * ctx, int32_t i) {
throw std::runtime_error(format("negative index out of range [0, %d)", ctx->n_outputs));
}
} else if ((size_t) i >= ctx->output_ids.size()) {
throw std::runtime_error(format("out of range [0, %lu)", ctx->output_ids.size()));
throw std::runtime_error(format("out of range [0, %zu)", ctx->output_ids.size()));
} else {
j = ctx->output_ids[i];
}