matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-12 08:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Re-remove cuda v11 (#10694)

Browse Source 
* 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
This commit is contained in:
Daniel Hiltgen
2025-06-23 14:07:00 -07:00
committed by GitHub
parent 2bb69b40c7
commit 1c6669e64c
14 changed files with 67 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llm/server.go
View File

@@ -311,7 +311,7 @@ func NewLlamaServer(gpus discover.GpuInfoList, modelPath string, f *ggml.GGML, a
params = append(params, "--mmproj", projectors[0])
}
// iterate through compatible GPU libraries such as 'cuda_v12', 'cuda_v11', 'rocm', etc.
// iterate through compatible GPU libraries such as 'cuda_v12', 'rocm', etc.
// adding each library's respective path to the LD_LIBRARY_PATH, until finally running
// without any LD_LIBRARY_PATH flags
for {