vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	CMakeLists.txt
#	README.md
#	ci/run.sh
#	docs/BLIS.md
#	flake.lock
#	grammars/README.md
This commit is contained in:
Concedo 2024-05-08 09:58:23 +08:00
commit bc39b4d98a
15 changed files with 94 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

36
examples/imatrix/imatrix.cpp
View file

@ -20,6 +20,7 @@
struct Stats {
std::vector<float> values;
std::vector<int> counts;
int ncall = 0;
};
@ -122,12 +123,10 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
auto & e = m_stats[wname];
++e.ncall;
// NOTE: since we select top-k experts, the number of calls for the expert tensors will be k times larger
// using the following line, we can correct for that if needed by replacing the line above with:
//if (idx == t->src[0]->ne[0] - 1) ++e.ncall;
if (e.values.empty()) {
e.values.resize(src1->ne[0]*n_as, 0);
e.counts.resize(src1->ne[0]*n_as, 0);
}
else if (e.values.size() != (size_t)src1->ne[0]*n_as) {
fprintf(stderr, "Oops: inconsistent size for %s (%d vs %d)\n", wname.c_str(), (int)e.values.size(), (int)src1->ne[0]*n_as);
@ -154,6 +153,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
for (int j = 0; j < (int)src1->ne[0]; ++j) {
e.values[e_start + j] += x[j]*x[j];
e.counts[e_start + j]++;
}
}
}
@ -171,6 +171,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
auto& e = m_stats[wname];
if (e.values.empty()) {
e.values.resize(src1->ne[0], 0);
e.counts.resize(src1->ne[0], 0);
}
else if (e.values.size() != (size_t)src1->ne[0]) {
fprintf(stderr, "Oops: inconsistent size for %s (%d vs %d)\n", wname.c_str(), (int)e.values.size(), (int)src1->ne[0]);
@ -184,6 +185,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
const float * x = data + row * src1->ne[0];
for (int j = 0; j < (int)src1->ne[0]; ++j) {
e.values[j] += x[j]*x[j];
e.counts[j]++;
}
}
if (e.ncall > m_last_call) {
@ -223,7 +225,13 @@ void IMatrixCollector::save_imatrix(const char * fname, const char * dataset) co
out.write((const char *) &p.second.ncall, sizeof(p.second.ncall));
int nval = p.second.values.size();
out.write((const char *) &nval, sizeof(nval));
if (nval > 0) out.write((const char *) p.second.values.data(), nval * sizeof(float));
if (nval > 0) {
std::vector<float> tmp(nval);
for (int i = 0; i < nval; i++) {
tmp[i] = (p.second.values[i] / static_cast<float>(p.second.counts[i])) * static_cast<float>(p.second.ncall);
}
out.write((const char*)tmp.data(), nval*sizeof(float));
}
}
// Write the number of call the matrix was computed with
@ -271,14 +279,28 @@ bool IMatrixCollector::load_imatrix(const char * imatrix_file, std::unordered_ma
imatrix_data = {};
return false;
}
e.values.resize(nval);
in.read((char*)e.values.data(), nval*sizeof(float));
// When re-called from load_imatrix() with add set, this will already be created.
if (e.values.empty()) {
e.values.resize(nval, 0);
e.counts.resize(nval, 0);
}
std::vector<float> tmp(nval);
in.read((char*)tmp.data(), nval*sizeof(float));
if (in.fail()) {
printf("%s: failed reading data for entry %d\n",__func__,i);
imatrix_data = {};
return false;
}
e.ncall = ncall;
// Recreate the state as expected by save_imatrix(), and corerct for weighted sum.
for (int i = 0; i < nval; i++) {
e.values[i] += tmp[i];
e.counts[i] += ncall;
}
e.ncall += ncall;
}
return true;
}