root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

llama : fix mlock with no-mmap with Metal (#5025)

Browse Source
This commit is contained in:
slaren 2024-01-18 21:12:15 +01:00 committed by GitHub
parent 2d5419d08a
commit 96d7f56d29
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llama.cpp
View File

@ -1599,7 +1599,7 @@ struct llama_model {
std::unique_ptr<llama_mmap> mapping;
// objects representing data potentially being locked in memory
llama_mlock mlock_buf;
std::vector<std::unique_ptr<llama_mlock>> mlock_bufs;
llama_mlock mlock_mmap;
// for quantize-stats only
@ -3815,8 +3815,10 @@ static bool llm_load_tensors(
else {
buf = ggml_backend_alloc_ctx_tensors_from_buft(ctx, buft);
if (buf != nullptr && use_mlock && ggml_backend_buffer_is_host(buf)) {
model.mlock_buf.init (ggml_backend_buffer_get_base(buf));
model.mlock_buf.grow_to(ggml_backend_buffer_get_size(buf));
model.mlock_bufs.emplace_back(new llama_mlock);
auto & mlock_buf = model.mlock_bufs.back();
mlock_buf->init (ggml_backend_buffer_get_base(buf));
mlock_buf->grow_to(ggml_backend_buffer_get_size(buf));
}
}
if (buf == nullptr) {