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

llama : extend API to get max devices at runtime (#2253)

Browse source
This commit is contained in:
Rinne 2023-07-19 15:06:40 +08:00 committed by GitHub
parent 45a1b07e9b
commit 294f424554
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
llama.cpp
View file

@ -875,6 +875,10 @@ struct llama_model_quantize_params llama_model_quantize_default_params() {
return result;
}
int llama_max_devices() {
return LLAMA_MAX_DEVICES;
}
bool llama_mmap_supported() {
return llama_mmap::SUPPORTED;
}

2
llama.h
View file

@ -153,6 +153,8 @@ extern "C" {
int32_t n_eval;
};
LLAMA_API int llama_max_devices();
LLAMA_API struct llama_context_params llama_context_default_params();
LLAMA_API struct llama_model_quantize_params llama_model_quantize_default_params();