root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 03:14:35 +00:00
Code Issues Actions 7 Packages Projects Releases Wiki Activity

ggml_tensor: update the structure comments. (#3283)

Browse Source 
* ggml_tensor: update the structure comments.

* remove semicolon

Co-authored-by: slaren <slarengh@gmail.com>

* Update ggml.h

---------

Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Hua Jiang 2023-09-28 13:06:18 -07:00 committed by GitHub
parent 7f1a0fe709
commit 0ccfc62a96
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml.h
View File

@ -473,8 +473,8 @@ extern "C" {
int n_dims; int n_dims;
int64_t ne[GGML_MAX_DIMS]; // number of elements int64_t ne[GGML_MAX_DIMS]; // number of elements
size_t nb[GGML_MAX_DIMS]; // stride in bytes: size_t nb[GGML_MAX_DIMS]; // stride in bytes:
// nb[0] = sizeof(type) // nb[0] = ggml_type_size(type)
// nb[1] = nb[0] * ne[0] + padding // nb[1] = nb[0] * (ne[0] / ggml_blck_size(type)) + padding
// nb[i] = nb[i-1] * ne[i-1] // nb[i] = nb[i-1] * ne[i-1]
// compute data // compute data