ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Honor mmap setting when using tensor overrides

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-03-19 17:05:04 +02:00
parent 22c84a126f
commit 1b62d0fae3
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -8015,7 +8015,7 @@ static bool llm_load_tensors(
// only the mmap region containing the tensors in the model is mapped to the backend buffer
// this is important for metal with apple silicon: if the entire model could be mapped to a metal buffer, then we could just use metal for all layers
// this allows using partial offloading when the model size exceeds the metal buffer size, but not the RAM size
if (ml.use_mmap && use_mmap_buffer && buft == llama_default_buffer_type_cpu(true)) {
if (ml.use_mmap && use_mmap_buffer && (buft == llama_default_buffer_type_cpu(true) || buft == ggml_backend_cpu_buffer_type())) {
for (uint32_t idx = 0; idx < ml.files.size(); idx++) {
void * addr = nullptr;
size_t first, last;