Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : shorten virtual device naming in CUDA and Metal (#27608)

Browse Source 
* ggml : shorten virtual device naming in CUDA and Metal

Assisted-by: llama.cpp:DeepSeek-V4-Flash-0731

* ggml-metal : build device description at init

Assisted-by: llama.cpp:DeepSeek-V4-Flash-0731

* cont : naming
This commit is contained in:
Georgi Gerganov
2026-08-24 12:35:08 +03:00
committed by GitHub
parent c1c766da59
commit a14dba686a
5 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.cpp
+2 -2
View File
@@ -17,10 +17,10 @@ struct ggml_metal_device_deleter {
typedef std::unique_ptr<ggml_metal_device, ggml_metal_device_deleter> ggml_metal_device_ptr;
ggml_metal_device_t ggml_metal_device_get(int device) {
ggml_metal_device_t ggml_metal_device_get(int device, int n_devices) {
static std::vector<ggml_metal_device_ptr> devs;
devs.emplace_back(ggml_metal_device_init(device));
devs.emplace_back(ggml_metal_device_init(device, n_devices));
return devs.back().get();
}