CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into xsn/private_batch_api

Browse Source
This commit is contained in:
Xuan Son Nguyen
2025-03-13 15:55:18 +01:00
parent 46596caf6d be7c303410
commit 17f954c8e2
173 changed files with 26425 additions and 16117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/imatrix/imatrix.cpp
View File

@@ -206,9 +206,6 @@ bool IMatrixCollector::collect_imatrix(struct ggml_tensor * t, bool ask, void *
void IMatrixCollector::save_imatrix(int ncall) const {
auto fname = m_params.out_file;
if (fname.empty()) {
fname = "imatrix.dat";
}
if (ncall > 0) {
fname += ".at_";
@@ -498,7 +495,7 @@ static bool compute_imatrix(llama_context * ctx, const common_params & params) {
const auto t_start = std::chrono::high_resolution_clock::now();
// clear the KV cache
llama_kv_cache_clear(ctx);
llama_kv_self_clear(ctx);
llama_batch_ext * batch = llama_batch_ext_init(n_batch, 1);
@@ -584,6 +581,8 @@ static bool compute_imatrix(llama_context * ctx, const common_params & params) {
int main(int argc, char ** argv) {
common_params params;
params.out_file = "imatrix.dat" ;
params.n_ctx = 512;
params.logits_all = true;
params.escape = false;