mirror of
https://github.com/ollama/ollama.git
synced 2025-07-22 14:23:20 +02:00
* Re-remove cuda v11
Revert the revert - drop v11 support requiring drivers newer than Feb 23
This reverts commit c6bcdc4223
.
* Simplify layout
With only one version of the GPU libraries, we can simplify things down somewhat. (Jetsons still require special handling)
* distinct sbsa variant for linux arm64
This avoids accidentally trying to load the sbsa cuda libraries on
a jetson system which results in crashes.
* temporary prevent rocm+cuda mixed loading
33 lines
1.3 KiB
Diff
33 lines
1.3 KiB
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Daniel Hiltgen <daniel@ollama.com>
|
|
Date: Sun, 22 Jun 2025 09:22:05 -0700
|
|
Subject: [PATCH] temporary prevent rocm+cuda mixed loading
|
|
|
|
---
|
|
ggml/src/ggml-backend-reg.cpp | 12 ++++++++++--
|
|
1 file changed, 10 insertions(+), 2 deletions(-)
|
|
|
|
diff --git a/ggml/src/ggml-backend-reg.cpp b/ggml/src/ggml-backend-reg.cpp
|
|
index 4e67d243..8f49f084 100644
|
|
--- a/ggml/src/ggml-backend-reg.cpp
|
|
+++ b/ggml/src/ggml-backend-reg.cpp
|
|
@@ -573,8 +573,16 @@ void ggml_backend_load_all_from_path(const char * dir_path) {
|
|
|
|
ggml_backend_load_best("blas", silent, dir_path);
|
|
ggml_backend_load_best("cann", silent, dir_path);
|
|
- ggml_backend_load_best("cuda", silent, dir_path);
|
|
- ggml_backend_load_best("hip", silent, dir_path);
|
|
+
|
|
+ // Avoid mixed hip+cuda configurations
|
|
+ const char * hip_devices = std::getenv("HIP_VISIBLE_DEVICES");
|
|
+ const char * rocr_devices = std::getenv("ROCR_VISIBLE_DEVICES");
|
|
+ if (!hip_devices && !rocr_devices) {
|
|
+ ggml_backend_load_best("cuda", silent, dir_path);
|
|
+ } else {
|
|
+ ggml_backend_load_best("hip", silent, dir_path);
|
|
+ }
|
|
+
|
|
ggml_backend_load_best("kompute", silent, dir_path);
|
|
ggml_backend_load_best("metal", silent, dir_path);
|
|
ggml_backend_load_best("rpc", silent, dir_path);
|