tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 12:25:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

imatrix : support 3d tensors with MUL_MAT

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-06-23 11:50:54 -04:00
parent 1a9454a3d2
commit 43cd2b3eb5
2 changed files with 53 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/quantize/quantize.cpp
View File

@ -196,7 +196,9 @@ static int load_legacy_imatrix(const std::string & imatrix_file, std::vector<std
exit(1);
}
if (ncall > 0) {
for (auto& v : e) v /= ncall;
for (auto & v : e) {
v /= ncall;
}
}
if (getenv("LLAMA_TRACE")) {