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

sync : ggml (Metal F32 support + reduce ggml-alloc size) (#3192)

Browse source 
* sync : ggml (Metal F32 support + reduce ggml-alloc size)

ggml-ci

* llama-bench : fix ggml_cpu_has_metal() duplicate function

ggml-ci
This commit is contained in:
Georgi Gerganov 2023-09-15 19:06:03 +03:00 • committed by GitHub
parent 7e50d34be6
commit 8c00b7a6ff
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 193 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

8
examples/llama-bench/llama-bench.cpp
View file

@ -74,14 +74,6 @@ static T stdev(const std::vector<T> & v) {
return stdev;
}
static bool ggml_cpu_has_metal() {
#if defined(GGML_USE_METAL)
return true;
#else
return false;
#endif
}
static std::string get_cpu_info() {
std::string id;
#ifdef __linux__