tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-26 03:03:25 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : sync (unary ops refactor, static-correctness) (#2370)

Browse Source 
* ggml : sync (unary ops, tests)

ggml-ci

* tests : remove unnecessary funcs
This commit is contained in:
Georgi Gerganov
2023-07-24 14:46:21 +03:00
committed by GitHub
parent 42f70cb2f6
commit 5b2b2dc6ae
6 changed files with 867 additions and 572 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/test-opt.c
View File

@ -125,9 +125,9 @@ int main(void) {
};
struct ggml_context * ctx = ggml_init(params);
int64_t ne1[4] = {4, 1024, 1, 1};
int64_t ne2[4] = {4, 2048, 1, 1};;
int64_t ne3[4] = {1024, 2048, 1, 1};
int64_t ne1[4] = {4, 128, 1, 1};
int64_t ne2[4] = {4, 256, 1, 1};;
int64_t ne3[4] = {128, 256, 1, 1};
struct ggml_tensor * a = get_random_tensor(ctx, 2, ne1, -1, +1);
struct ggml_tensor * b = get_random_tensor(ctx, 2, ne2, -1, +1);