happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml-zdnn: fix errorenous output load tensor 

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
This commit is contained in:
Aaron Teo 2025-07-30 16:11:07 +08:00
parent 20d69b6cdf
commit 4d5edb2221
No known key found for this signature in database
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-zdnn/ggml-zdnn-rewrite.cpp
View File

@ -136,7 +136,7 @@ static void ggml_zdnn_mul_mat_op(ggml_backend_zdnn_context * ctx, const ggml_ten
ggml_zdnn_load_tensor(weights_extra->ztensor, weights->data);
ggml_zdnn_load_tensor(inputs_extra->ztensor, inputs->data);
ggml_zdnn_load_tensor(zt_bias, bias_data);
ggml_zdnn_load_tensor(output_extra->ztensor, output->data);
// ggml_zdnn_load_tensor(output_extra->ztensor, output->data);
// GGML_LOG_INFO("%s: tensor '%s' tensor dimensions: [%ld, %ld, %ld, %ld] pre_tfm_desc dimensions: [%ld, %ld, %ld, %ld]\n",
// __func__, weights_extra->name,