jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

quantize : fix minor logic flaw in --tensor-type (#14572)

Browse Source
This commit is contained in:
Ed Addario 2025-07-13 17:02:17 +01:00 committed by GitHub
parent 923e3ea2e3
commit 982e347255
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-quant.cpp
View File

@ -884,8 +884,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
if (std::regex pattern(tname); std::regex_search(tensor_name, pattern)) {
if (qtype != new_type) {
LLAMA_LOG_DEBUG("(overriding %s) ", ggml_type_name(new_type));
new_type = qtype;
break; // if two or more types are specified for the tensor, first match wins
new_type = qtype; // if two or more types are specified for the same tensor, the last match wins
}
}
}