tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

make the CI fail GitHub Actions on test failures (#3517)

Browse Source 
* make the CI fail GitHub Actions on test failures

* use model bundle

* install zstd for compressed model artifact
This commit is contained in:
Wing Lian
2026-03-19 08:29:24 -04:00
committed by GitHub
parent 163bd4dd5a
commit bb483ad4c4
4 changed files with 11 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
cicd/Dockerfile-uv.jinja
View File

@@ -11,7 +11,7 @@ ENV NIGHTLY_BUILD="{{ NIGHTLY_BUILD }}"
ENV HF_HOME="{{ HF_HOME }}"
RUN apt-get update && \
apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
apt-get install -y --allow-change-held-packages vim curl nano zstd libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
WORKDIR /workspace

2
cicd/Dockerfile.jinja
View File

@@ -12,7 +12,7 @@ ENV HF_HOME="{{ HF_HOME }}"
ENV AXOLOTL_DATASET_NUM_PROC="8"
RUN apt-get update && \
apt-get install -y --allow-change-held-packages vim curl nano libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
apt-get install -y --allow-change-held-packages vim curl nano zstd libnccl2 libnccl-dev ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm
WORKDIR /workspace

11
cicd/cicd.sh
View File

@@ -3,11 +3,12 @@ set -e
python -c "import torch; assert '$PYTORCH_VERSION' in torch.__version__"
# curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst | tar -xpf - -C "${HF_HOME}/hub/" --use-compress-program unzstd --strip-components=1
hf download "NousResearch/Meta-Llama-3-8B"
hf download "NousResearch/Meta-Llama-3-8B-Instruct"
hf download "microsoft/Phi-4-reasoning"
hf download "microsoft/Phi-3.5-mini-instruct"
curl -L https://axolotl-ci.b-cdn.net/hf-cache.tar.zst | tar -xpf - -C "${HF_HOME}/hub/" --use-compress-program unzstd --strip-components=1
# hf download "NousResearch/Meta-Llama-3-8B"
# hf download "NousResearch/Meta-Llama-3-8B-Instruct"
# hf download "microsoft/Phi-4-reasoning"
# hf download "microsoft/Phi-3.5-mini-instruct"
# hf download "microsoft/Phi-3-medium-128k-instruct"
# Run unit tests with initial coverage report
pytest -v --durations=10 -n8 \

10
cicd/single_gpu.py
View File

@@ -68,10 +68,6 @@ def run_cmd(cmd: str, run_folder: str):
sp_env["AXOLOTL_DATASET_NUM_PROC"] = "8"
# Propagate errors from subprocess.
try:
exit_code = subprocess.call(cmd.split(), cwd=run_folder, env=sp_env) # nosec
if exit_code:
print(f"Command '{cmd}' failed with exit code {exit_code}")
return exit_code
except Exception as e: # pylint: disable=broad-except
print(f"Command '{cmd}' failed with exception {e}")
exit_code = subprocess.call(cmd.split(), cwd=run_folder, env=sp_env) # nosec
if exit_code:
raise RuntimeError(f"Command '{cmd}' failed with exit code {exit_code}")