ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-29 02:41:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: set compute parameters via command line arguments (#910)

Browse Source 
* cuda: set compute parameters via command line arguments

* Also llama-bench

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-11-07 07:11:23 +02:00
committed by GitHub
parent 665434e5ec
commit 9d0b834405
11 changed files with 144 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/include/ggml-cuda.h
View File

@@ -21,7 +21,7 @@ extern "C" {
#define GGML_CUDA_MAX_DEVICES 16
// backend API
GGML_API GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device);
GGML_API GGML_CALL ggml_backend_t ggml_backend_cuda_init(int device, const void * params);
GGML_API GGML_CALL bool ggml_backend_is_cuda(ggml_backend_t backend);