CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

gguf : start implementing quantization (WIP)

Browse Source
This commit is contained in:
M. Yusuf Sarıgöz
2023-08-12 12:01:17 +03:00
parent 0e1a3c7e7d
commit c4f02b4f74
2 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
gguf-llama.cpp
View File

@@ -778,8 +778,7 @@ struct gguf_file_saver {
}
write_tensor_info(tensor);
// file.write_raw(new_data);
GGML_UNUSED(new_data);
file.write_raw(new_data, new_size);
size_t padded_size = GGML_PAD(new_size, GGUF_DEFAULT_ALIGNMENT); // TODO: handle custom alignment
size_t pad = padded_size - new_size;
file.write_zeros(pad);