Skip to content

Commit 3be3ba3

Browse files
committed
Fix a typo when calcualte VRAM size
1 parent 4612bf5 commit 3be3ba3

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

llama.cpp

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1061,8 +1061,8 @@ static void llama_model_load_internal(
10611061

10621062
if (backend == GGML_BACKEND_CUDA) {
10631063
vram_total +=
1064-
ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) +
1065-
ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.attention_norm) +
1064+
ggml_nbytes(layer.attention_norm) + ggml_nbytes(layer.wq) + ggml_nbytes(layer.wk) +
1065+
ggml_nbytes(layer.wv) + ggml_nbytes(layer.wo) + ggml_nbytes(layer.ffn_norm) +
10661066
ggml_nbytes(layer.w1) + ggml_nbytes(layer.w2) + ggml_nbytes(layer.w3);
10671067
}
10681068
}

0 commit comments

Comments
 (0)