chore: import upstream snapshot with attribution

This commit is contained in:
wehub-resource-sync
2026-07-13 13:17:40 +08:00
commit f1825c8ceb
10096 changed files with 2364182 additions and 0 deletions
@@ -0,0 +1,19 @@
cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }}
region: us-west-2
# Cluster resources
head_node_type:
name: head
instance_type: m5.2xlarge
resources:
cpu: 8
worker_node_types:
- name: 16CPU-64GB
instance_type: m8i.4xlarge
min_workers: 1
max_workers: 32
- name: 4CPU-16GB-1GPU
instance_type: g6.xlarge
min_workers: 1
max_workers: 32
+21
View File
@@ -0,0 +1,21 @@
#!/bin/bash
set -euxo pipefail
# Install Python dependencies
pip3 install --no-cache-dir \
"numpy>=1.24.0,<2.0" \
"torch>=2.0.0" \
"transformers>=4.35.0" \
"accelerate>=0.25.0" \
"sentencepiece>=0.1.99" \
"httpx>=0.25.0" \
"aioboto3>=12.0.0" \
"pillow>=10.0.0"
sudo apt-get update && sudo apt-get install -y --no-install-recommends \
ffmpeg \
&& sudo rm -rf /var/lib/apt/lists/*
export S3_BUCKET=anyscale-example-video-analysis-test-bucket
@@ -0,0 +1,19 @@
cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }} # required; set by CI
region: us-central1
# Cluster resources
head_node_type:
name: head
instance_type: n1-standard-8
resources:
cpu: 8
worker_node_types:
- name: 16CPU-64GB-GPU
instance_type: n4-standard-16
min_workers: 1
max_workers: 32
- name: 4CPU-16GB-GPU
instance_type: g2-standard-4
min_workers: 1
max_workers: 32
@@ -0,0 +1,40 @@
#!/usr/bin/env python3
import argparse
import nbformat
def convert_notebook(input_path: str, output_path: str) -> None:
"""
Read a Jupyter notebook and write a Python script.
Cells that load or autoreload extensions are ignored.
"""
nb = nbformat.read(input_path, as_version=4)
with open(output_path, "w") as out:
for cell in nb.cells:
if cell.cell_type != "code":
continue
lines = cell.source.splitlines()
# Skip cells that load or autoreload extensions
if any(
l.strip().startswith("%load_ext autoreload")
or l.strip().startswith("%autoreload all")
for l in lines
):
continue
out.write(cell.source.rstrip() + "\n\n")
def main() -> None:
parser = argparse.ArgumentParser(
description="Convert a Jupyter notebook to a Python script."
)
parser.add_argument("input_nb", help="Path to the input .ipynb file")
parser.add_argument("output_py", help="Path for the output .py script")
args = parser.parse_args()
convert_notebook(args.input_nb, args.output_py)
if __name__ == "__main__":
main()
+11
View File
@@ -0,0 +1,11 @@
#!/bin/bash
set -euxo pipefail
S3_BUCKET=anyscale-example-video-analysis-test-bucket
export S3_BUCKET
python ci/nb2py.py README.ipynb README.py # convert notebook to py script
python README.py
rm README.py # remove the generated script