frozenleaves/DeepSpeed
1
0
Fork 0
mirror of https://github.com/deepspeedai/DeepSpeed.git synced 2025-10-20 15:33:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update A6000 workflows to use newer docker container - 24.09 vs 24.03 (#6967)

Browse Source 
- Issues with nv-sd updates, will follow up with a subsequent PR
This commit is contained in:
Logan Adams
2025-01-31 15:07:12 -08:00
committed by GitHub
parent 029e0a33d6
commit 241bffded3
3 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.github/workflows/nv-a6000.yml vendored
View File

@ -23,7 +23,7 @@ jobs:
unit-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:24.03-py3
image: nvcr.io/nvidia/pytorch:24.09-py3
ports:
- 80
options: --gpus all --shm-size "8G"
@ -57,8 +57,8 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.3" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.3" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2' unit/ --torch_ver="2.5" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'inference_v2_ops' unit/ --torch_ver="2.5" --cuda_ver="12"
- name: MII unit tests
run: |
BRANCH="main"

4
.github/workflows/nv-flash-attn.yml vendored
View File

@ -18,7 +18,7 @@ jobs:
unit-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:24.03-py3
image: nvcr.io/nvidia/pytorch:24.09-py3
ports:
- 80
options: --gpus all --shm-size "8G"
@ -53,7 +53,7 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.3" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF unit/sequence_parallelism/test_ulysses.py --torch_ver="2.5" --cuda_ver="12"
- name: Open GitHub issue if nightly CI fails
if: ${{ failure() && (github.event_name == 'schedule') }}
uses: JasonEtco/create-an-issue@v2

4
.github/workflows/nv-human-eval.yml vendored
View File

@ -11,7 +11,7 @@ jobs:
unit-tests:
runs-on: [self-hosted, nvidia, a6000]
container:
image: nvcr.io/nvidia/pytorch:24.03-py3
image: nvcr.io/nvidia/pytorch:24.09-py3
ports:
- 80
options: --gpus all --shm-size "8G"
@ -50,4 +50,4 @@ jobs:
run: |
unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch
cd tests
python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.3" --cuda_ver="12"
python -m pytest --color=yes --durations=0 --verbose -rF -m 'evaluation' -k "test_human_eval" unit/ --torch_ver="2.5" --cuda_ver="12"