Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix not enough space in buffer with Qwen (#5086)

Browse Source
This commit is contained in:
slaren 2024-01-22 23:42:41 +01:00 committed by GitHub
parent 6f9939d119
commit 011e8ec577
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@ -4440,9 +4440,9 @@ static struct ggml_tensor * llm_build_kv(
// these nodes are added to the graph together so that they are not reordered
// by doing so, the number of splits in the graph is reduced
ggml_build_forward_expand(graph, q_cur);
ggml_build_forward_expand(graph, k_cur);
ggml_build_forward_expand(graph, v_cur);
ggml_build_forward_expand(graph, q_cur);
llm_build_kv_store(ctx, hparams, kv, graph, k_cur, v_cur, n_ctx, n_tokens, kv_head, cb, il);