vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

CUDA 11.4 for Github CI (#582)

Browse source 
* Downgrade CUDA to 11.4

This helps the binary be smaller and adds K80 support, the manual compiles we did already had this.

* Update kcpp-build-release-win-cuda.yaml

* Update kcpp-build-release-win-cuda.yaml

* Update kcpp-build-release-win-cuda.yaml

* Update kcpp-build-release-win-cuda.yaml

* Update kcpp-build-release-win-cuda.yaml

* Update kcpp-build-release-win-cuda.yaml

* Restore concedo_experimental
This commit is contained in:
henk717 2023-12-26 04:23:43 +01:00 • committed by GitHub
parent c2d87b6545
commit 5006b23099
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

10
.github/workflows/kcpp-build-release-win-cuda.yaml vendored
View file

@ -6,7 +6,7 @@ env:
jobs: jobs:
windows: windows:
runs-on: windows-latest runs-on: windows-2019
steps: steps:
- name: Clone - name: Clone
id: checkout id: checkout
@ -17,16 +17,14 @@ jobs:
- uses: Jimver/cuda-toolkit@v0.2.11 - uses: Jimver/cuda-toolkit@v0.2.11
id: cuda-toolkit id: cuda-toolkit
with: with:
cuda: '11.7.1' cuda: '11.4.4'
method: 'network'
sub-packages: '["nvcc", "cudart", "cublas", "cublas_dev", "thrust", "visual_studio_integration"]'
- name: Build - name: Build
id: cmake_build id: cmake_build
run: | run: |
mkdir build mkdir build
cd build cd build
cmake .. -DLLAMA_CUBLAS=ON cmake .. -DLLAMA_CUBLAS=ON -DCMAKE_SYSTEM_VERSION="10.0.19041.0"
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
- name: Save artifact - name: Save artifact