CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

examples : replace llama_kv_cache_seq_* with llama_past_seq_*

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-10 14:44:42 -04:00
parent 372482dffe
commit 43d8d4bf9e
23 changed files with 125 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/imatrix/imatrix.cpp
View File

@@ -455,7 +455,7 @@ static bool compute_imatrix(llama_context * ctx, const gpt_params & params) {
const auto t_start = std::chrono::high_resolution_clock::now();
// clear the KV cache
llama_kv_cache_clear(ctx);
llama_past_clear(ctx);
for (int j = 0; j < num_batches; ++j) {
const int batch_start = start + j * n_batch;