CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ci : adjust params for less runtime (#16167)

Browse Source 
* ci : adjust params for less runtime

* ci : gate BF16 on some hardware

* ci : move extra tests to Arm runner
This commit is contained in:
Georgi Gerganov
2025-09-22 08:31:40 +03:00
committed by GitHub
parent 9073a73d82
commit 4d0a7cbc61
3 changed files with 44 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/build.yml vendored
View File

@@ -1300,7 +1300,7 @@ jobs:
- name: Test
id: ggml-ci
run: |
bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
GG_BUILD_NO_BF16=1 GG_BUILD_EXTRA_TESTS_0=1 bash ./ci/run.sh ~/results/llama.cpp /mnt/llama.cpp
ggml-ci-x64-nvidia-v100-cuda:
runs-on: [self-hosted, Linux, X64, NVIDIA, V100]