thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

memory : remove unused tmp_buf (#19199)

Browse source 
This commit removes the unused tmp_buf variable from llama-kv-cache.cpp
and llama-memory-recurrent.cpp.

The tmp_buf variable was declared but never used but since it has a
non-trivial constructor/desctuctor we don't get an unused variable
warning about it.
This commit is contained in:
Daniel Bevenius 2026-01-30 10:37:06 +01:00 • committed by GitHub
parent b316895ff9
commit 83bcdf7217
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

8
src/llama-kv-cache.cpp
View file

@ -1772,8 +1772,6 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
io.write(&v_trans, sizeof(v_trans));
io.write(&n_layer, sizeof(n_layer));
std::vector<uint8_t> tmp_buf;
// Iterate and write all the keys first, each row is a cell
// Get whole range at a time
for (const auto & layer : layers) {
@ -1791,7 +1789,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
const uint64_t k_size_row = ggml_row_size(k->type, n_embd_k_gqa);
io.write(&k_size_row, sizeof(k_size_row));
// Read each range of cells of k_size length each into tmp_buf and write out
// Read each range of cells of k_size length and write out
for (const auto & range : cr.data) {
const size_t range_size = range.second - range.first;
const size_t buf_size = range_size * k_size_row;
@ -1818,7 +1816,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
const uint64_t v_size_row = ggml_row_size(v->type, n_embd_v_gqa);
io.write(&v_size_row, sizeof(v_size_row));
// Read each range of cells of v_size length each into tmp_buf and write out
// Read each range of cells of v_size length and write out
for (const auto & range : cr.data) {
const size_t range_size = range.second - range.first;
const size_t buf_size = range_size * v_size_row;
@ -1852,7 +1850,7 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t
// For each row, we get the element values of each cell
for (uint32_t j = 0; j < n_embd_v_gqa; ++j) {
// Read each range of cells of v_size_el length each into tmp_buf and write out
// Read each range of cells of v_size_el length and write out
for (const auto & range : cr.data) {
const size_t range_size = range.second - range.first;
const size_t src_offset = (range.first + j * kv_size) * v_size_el;