highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-09-20 10:01:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

Add compute capability 5.0, 7.5, and 8.0

Browse Source
This commit is contained in:
Daniel Hiltgen
2024-01-20 12:15:50 -08:00
parent 681a914990
commit a447a083f2
5 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/development.md
View File

@@ -50,7 +50,8 @@ development and runtime packages.
Typically the build scripts will auto-detect CUDA, however, if your Linux distro
or installation approach uses unusual paths, you can specify the location by
specifying an environment variable `CUDA_LIB_DIR` to the location of the shared
libraries, and `CUDACXX` to the location of the nvcc compiler.
libraries, and `CUDACXX` to the location of the nvcc compiler. You can customize
set set of target CUDA architectues by setting `CMAKE_CUDA_ARCHITECTURES` (e.g. "50;60;70")
Then generate dependencies: