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 commit 'ad3a0505e3' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/code-coverage.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/server.yml
#	.github/workflows/zig-build.yml
#	.gitignore
#	CMakeLists.txt
#	Makefile
#	README-sycl.md
#	README.md
#	build.zig
#	common/CMakeLists.txt
#	llama.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-04-06 18:32:57 +08:00
commit 9c0fbf9f73
67 changed files with 10861 additions and 4661 deletions
Download patch file Download diff file Expand all files Collapse all files

39
examples/imatrix/imatrix.cpp
View file

@ -51,29 +51,31 @@ private:
void keep_imatrix(int ncall) const;
};
// remove any prefix and suffixes from the name
// CUDA0#blk.0.attn_k.weight#0 => blk.0.attn_k.weight
static std::string filter_tensor_name(const char * name) {
std::string wname;
const char * p = strchr(name, '#');
if (p != NULL) {
p = p + 1;
const char * q = strchr(p, '#');
if (q != NULL) {
wname = std::string(p, q - p);
} else {
wname = p;
}
} else {
wname = name;
}
return wname;
}
bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void * user_data) {
GGML_UNUSED(user_data);
const struct ggml_tensor * src0 = t->src[0];
const struct ggml_tensor * src1 = t->src[1];
std::string wname;
{
// remove any prefix and suffixes from the name
// CUDA0#blk.0.attn_k.weight#0 => blk.0.attn_k.weight
const char * p = strchr(src0->name, '#');
if (p != NULL) {
p = p + 1;
const char * q = strchr(p, '#');
if (q != NULL) {
wname = std::string(p, q - p);
} else {
wname = p;
}
} else {
wname = src0->name;
}
}
std::string wname = filter_tensor_name(src0->name);
// when ask is true, the scheduler wants to know if we are interested in data from this tensor
// if we return true, a follow-up call will be made with ask=false in which we can do the actual collection
@ -113,6 +115,7 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
// this is necessary to guarantee equal number of "ncall" for each tensor
for (int ex = 0; ex < n_as; ++ex) {
src0 = t->src[2 + ex];
wname = filter_tensor_name(src0->name);
auto& e = m_stats[wname];
if (e.values.empty()) {
e.values.resize(src1->ne[0], 0);