ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml : portability fixes for VS 2017 (#12150)

Browse source 
* Add include files for std::min/max and std::toupper/tolower

* win32: move _USE_MATH_DEFINES before includes to ensure M_PI is defined

* Use GGML_RESTRICT instead of "restrict" keyword everywhere, and use "__restrict" in MSVC plain C mode

* win32: only use __restrict in MSVC if C11/C17 support is not enabled

---------

Co-authored-by: Marcus Groeber <Marcus.Groeber@cerence.com>
This commit is contained in:
mgroeber9110 2025-03-04 17:53:26 +01:00 • committed by GitHub
parent 20a9b8f5e1
commit 5bbe6a9fe9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 547 additions and 529 deletions
Download patch file Download diff file Expand all files Collapse all files

1
common/ngram-cache.cpp
View file

@ -7,6 +7,7 @@
#include <cstdio>
#include <fstream>
#include <thread>
#include <algorithm>
void common_ngram_cache_update(common_ngram_cache & ngram_cache, int ngram_min, int ngram_max,
std::vector<llama_token> & inp, int nnew, bool print_progress) {