vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : fix op mul check with command-r-plus

Browse source
This commit is contained in:
slaren 2024-11-24 15:48:00 +01:00
parent 9336db462c
commit f519ac63c6
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
src/llama.cpp
View file

@ -7181,12 +7181,12 @@ static bool weight_buft_supported(const llama_hparams & hparams, ggml_tensor * w
} break;
case GGML_OP_ADD:
{
ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
op_tensor = ggml_add(ctx, a, w);
} break;
case GGML_OP_MUL:
{
ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, w->ne[0], 512);
ggml_tensor * a = ggml_new_tensor_4d(ctx, GGML_TYPE_F32, w->ne[0], w->ne[1], w->ne[2], w->ne[3]);
op_tensor = ggml_mul(ctx, a, w);
} break;
case GGML_OP_DIV: