sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests 1 Actions 175 Packages Projects Releases Wiki Activity

ggml : remove GGML_KQ_MASK_PAD constant (#17910)

Browse Source 
* ggml : remove GGML_KQ_MASK_PAD constant

* cont : remove comment
This commit is contained in:
Georgi Gerganov
2025-12-10 20:53:16 +02:00
committed by GitHub
parent 4df6e859e9
commit 4dff236a52
7 changed files with 19 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-kv-cache.cpp
+2 -3
View File
@@ -1232,8 +1232,7 @@ void llama_kv_cache::set_input_kq_mask(ggml_tensor * dst, const llama_ubatch * u
GGML_ASSERT(n_tokens%n_stream == 0);
// n_tps == n_tokens_per_stream
const int64_t n_tps = n_tokens/n_stream;
const int64_t n_tps_pad = GGML_PAD(n_tps, GGML_KQ_MASK_PAD);
const int64_t n_tps = n_tokens/n_stream;
std::fill(data, data + ggml_nelements(dst), -INFINITY);
@@ -1266,7 +1265,7 @@ void llama_kv_cache::set_input_kq_mask(ggml_tensor * dst, const llama_ubatch * u
const llama_pos p1_x = is_2d ? ubatch->pos[i + ubatch->n_tokens*2] : 0;
const llama_pos p1_y = is_2d ? ubatch->pos[i + ubatch->n_tokens] : 0;
const uint64_t idst = n_kv*(h*n_stream*n_tps_pad + s*n_tps_pad + ii);
const uint64_t idst = n_kv*(h*n_stream*n_tps + s*n_tps + ii);
for (uint32_t j = 0; j < n_kv; ++j) {
if (cells.is_empty(j)) {