CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove unused data and add fixes (#5154)

Browse Source 
* Remove unused data and add fixes

* Add missing file

* Address review comments

* Replace the scope of vq allocation
This commit is contained in:
Michael Klimenko
2024-01-27 15:25:55 +01:00
committed by GitHub
parent ec903c0341
commit 35a2ee9143
7 changed files with 3 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
pocs/vdot/vdot.cpp
View File

@@ -243,7 +243,6 @@ int main(int argc, char** argv) {
if (useQ4_1) q41.resize(n4);
else q40.resize(n4);
std::vector<block_q8_0> q8(n8);
std::vector<int64_t> H(16, 0);
double sumt = 0, sumt2 = 0, maxt = 0;
double sumqt = 0, sumqt2 = 0, maxqt = 0;
double sum = 0, sumq = 0, exactSum = 0;