ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make sure we do have wk_b and wv_b before enabling MLA

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-02-09 09:24:52 +02:00
parent 7cdb0a1ec3
commit bf1d056125
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -3175,7 +3175,7 @@ static bool llama_kv_cache_init(
struct ggml_context * ctx = offload ? ctx_map.at(model.buft_layer[i].buft) : cache.ctxs.front();
ggml_tensor * k;
ggml_tensor * v;
if (cparams.mla_attn) {
if (cparams.mla_attn && model.layers[i].wk_b && model.layers[i].wv_b) {
k = ggml_new_tensor_1d(ctx, type_k, 1);
v = ggml_new_tensor_1d(ctx, type_v, 1);
}