CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix lambda capture

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2023-08-17 19:49:21 +03:00
parent 93f285bdf1
commit 899f9a5350
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
llama.cpp
View File

@@ -3576,7 +3576,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
new_data = work.data(); new_data = work.data();
std::vector<int64_t> hist_cur(1 << 4, 0); std::vector<int64_t> hist_cur(1 << 4, 0);
const int chunk_size = 32 * 512; static const int chunk_size = 32 * 512;
const int nchunk = (nelements + chunk_size - 1)/chunk_size; const int nchunk = (nelements + chunk_size - 1)/chunk_size;
const int nthread_use = nthread > 1 ? std::max(1, std::min(nthread, nchunk)) : 1; const int nthread_use = nthread > 1 ? std::max(1, std::min(nthread, nchunk)) : 1;
if (nthread_use < 2) { if (nthread_use < 2) {
@@ -3584,7 +3584,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
} else { } else {
size_t counter = 0; size_t counter = 0;
new_size = 0; new_size = 0;
auto compute = [&mutex, &counter, &hist_cur, &new_size, new_type, f32_data, new_data, nelements, chunk_size]() { // NOLINT auto compute = [&mutex, &counter, &hist_cur, &new_size, new_type, f32_data, new_data, nelements]() {
std::vector<int64_t> local_hist; std::vector<int64_t> local_hist;
size_t local_size = 0; size_t local_size = 0;
while (true) { while (true) {