cf0c79d52e
* fix: update chat_template * fix: handle gemma3 showing a lot of no content for turn 0 * fix: remove unknown config from examples * fix: test * fix: temporary disable gemma2 test * fix: stop overwriting config.text_config unnecessarily * fix: handling of set cache to the text_config section * feat: add liger gemma support and bump liger to 0.5.5 * fix: add double use_cache setting * fix: add support for final_logit_softcap in CCE for gemma2/3 * fix: set use_cache before model load * feat: add missing layernorm override * fix: handle gemma3 rmsnorm * fix: use wrapper to pass dim as hidden_size * fix: change dim to positional * fix: patch with wrong mlp * chore: refactor use_cache handling * fix import issues * fix tests.e2e.utils import --------- Co-authored-by: Wing Lian <wing@axolotl.ai>
83 lines
2.2 KiB
Python
83 lines
2.2 KiB
Python
"""Modal app to run axolotl GPU tests"""
|
|
|
|
# pylint: disable=duplicate-code
|
|
|
|
import os
|
|
import pathlib
|
|
import tempfile
|
|
|
|
import jinja2
|
|
import modal
|
|
from jinja2 import select_autoescape
|
|
from modal import App, Image
|
|
|
|
cicd_path = pathlib.Path(__file__).parent.resolve()
|
|
|
|
template_loader = jinja2.FileSystemLoader(searchpath=cicd_path)
|
|
template_env = jinja2.Environment(
|
|
loader=template_loader, autoescape=select_autoescape()
|
|
)
|
|
df_template = template_env.get_template("Dockerfile.jinja")
|
|
|
|
df_args = {
|
|
"AXOLOTL_EXTRAS": os.environ.get("AXOLOTL_EXTRAS", ""),
|
|
"AXOLOTL_ARGS": os.environ.get("AXOLOTL_ARGS", ""),
|
|
"PYTORCH_VERSION": os.environ.get("PYTORCH_VERSION", "2.4.1"),
|
|
"BASE_TAG": os.environ.get("BASE_TAG", "main-base-py3.11-cu121-2.4.1"),
|
|
"CUDA": os.environ.get("CUDA", "121"),
|
|
"GITHUB_REF": os.environ.get("GITHUB_REF", "refs/heads/main"),
|
|
"GITHUB_SHA": os.environ.get("GITHUB_SHA", ""),
|
|
"NIGHTLY_BUILD": os.environ.get("NIGHTLY_BUILD", ""),
|
|
"HF_HOME": "/workspace/data/huggingface-cache/hub",
|
|
}
|
|
|
|
dockerfile_contents = df_template.render(**df_args)
|
|
|
|
temp_dir = tempfile.mkdtemp()
|
|
with open(pathlib.Path(temp_dir) / "Dockerfile", "w", encoding="utf-8") as f:
|
|
f.write(dockerfile_contents)
|
|
|
|
cicd_image = Image.from_dockerfile(
|
|
pathlib.Path(temp_dir) / "Dockerfile",
|
|
context_mount=None,
|
|
force_build=True,
|
|
gpu="A10G",
|
|
).env(df_args)
|
|
|
|
app = App("Axolotl CI/CD", secrets=[])
|
|
|
|
hf_cache_volume = modal.Volume.from_name(
|
|
"axolotl-ci-hf-hub-cache", create_if_missing=True
|
|
)
|
|
VOLUME_CONFIG = {
|
|
"/workspace/data/huggingface-cache/hub": hf_cache_volume,
|
|
}
|
|
|
|
N_GPUS = int(os.environ.get("N_GPUS", 1))
|
|
GPU_CONFIG = modal.gpu.L40S(count=N_GPUS)
|
|
|
|
|
|
def run_cmd(cmd: str, run_folder: str):
|
|
import subprocess # nosec
|
|
|
|
# Propagate errors from subprocess.
|
|
if exit_code := subprocess.call(cmd.split(), cwd=run_folder): # nosec
|
|
exit(exit_code) # pylint: disable=consider-using-sys-exit
|
|
|
|
|
|
@app.function(
|
|
image=cicd_image,
|
|
gpu=GPU_CONFIG,
|
|
timeout=60 * 60,
|
|
cpu=8.0,
|
|
memory=131072,
|
|
volumes=VOLUME_CONFIG,
|
|
)
|
|
def cicd_pytest():
|
|
run_cmd("./cicd/cicd.sh", "/workspace/axolotl")
|
|
|
|
|
|
@app.local_entrypoint()
|
|
def main():
|
|
cicd_pytest.remote()
|