Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 2b0d3f3

Browse filesBrowse files
abetlenabetlen
committed
set llama_max_devices using library function
1 parent d9a1d90 commit 2b0d3f3
Copy full SHA for 2b0d3f3

File tree

Expand file treeCollapse file tree

1 file changed

+1
-3
lines changed
Filter options
Expand file treeCollapse file tree

1 file changed

+1
-3
lines changed

‎llama_cpp/llama_cpp.py

Copy file name to clipboardExpand all lines: llama_cpp/llama_cpp.py
+1-3Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -90,9 +90,7 @@ def _load_shared_library(lib_base_name: str):
9090

9191
# llama.h bindings
9292

93-
GGML_USE_CUBLAS = hasattr(_lib, "ggml_init_cublas")
94-
GGML_CUDA_MAX_DEVICES = 16
95-
LLAMA_MAX_DEVICES = GGML_CUDA_MAX_DEVICES if GGML_USE_CUBLAS else 1
93+
LLAMA_MAX_DEVICES = _lib.llama_max_devices()
9694

9795
# define LLAMA_DEFAULT_SEED 0xFFFFFFFF
9896
LLAMA_DEFAULT_SEED = 0xFFFFFFFF

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.