LLM-Inference/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-08-12 22:29:39 +04:00
Code Issues Packages Projects Releases Wiki Activity

Reduce the indexer temporary buffer size

Browse Source
This commit is contained in:
Kawrakow
2026-08-07 14:05:30 +00:00
parent 36925b86c1
commit d7836010a1
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/indexer_topk.cu
+1 -1
View File
@@ -146,7 +146,7 @@ void ggml_cuda_op_indexer_topk(ggml_backend_cuda_context & ctx, ggml_tensor * ds
}
constexpr int64_t k_max_work_buffer_elements = 1 << 28;
constexpr int64_t k_max_work_buffer_elements = 1 << 26;
int max_rows = k_max_work_buffer_elements / n_kv / n_head;
if (max_rows < 1) max_rows = 1;