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

iq2_xs: CUDA and scalar CPU works

Browse source
This commit is contained in:
Iwan Kawrakow 2024-01-09 18:19:02 +02:00
parent 9f21b82e4b
commit 9b6e38d8c0
5 changed files with 669 additions and 111 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ggml.c
View file

@ -19055,8 +19055,8 @@ struct gguf_context * gguf_init_from_file(const char * fname, struct gguf_init_p
(int64_t) info->ne[3];
if (ne % ggml_blck_size(info->type) != 0) {
fprintf(stderr, "%s: tensor '%s' number of elements (%" PRId64 ") is not a multiple of block size (%d)\n",
__func__, info->name.data, ne, ggml_blck_size(info->type));
fprintf(stderr, "%s: tensor '%s' of type %d (%s) number of elements (%" PRId64 ") is not a multiple of block size (%d)\n",
__func__, info->name.data, (int)info->type, ggml_type_name(info->type), ne, ggml_blck_size(info->type));
fclose(file);
gguf_free(ctx);
return NULL;