tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : move AMX to the CPU backend (#10570)

Browse Source 
* ggml : move AMX to the CPU backend

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Diego Devesa
2024-11-29 21:54:58 +01:00
committed by GitHub
parent b782e5c7d4
commit 7cc2d2c889
64 changed files with 514 additions and 801 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/test-sampling.cpp
View File

@ -284,7 +284,7 @@ static void test_perf() {
data.reserve(n_vocab);
for (int i = 0; i < n_vocab; i++) {
const float logit = 2.0f*((float)(rand())/RAND_MAX - 0.5f);
const float logit = 2.0f*((double)(rand())/RAND_MAX - 0.5);
data.emplace_back(llama_token_data{i, logit, 0.0f});
}