ivanwu/helm-charts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: bugs for interuption of downloading model

Browse Source
This commit is contained in:
Ivan087
2025-12-02 15:43:05 +08:00
parent ad350ee5ad
commit fccbb10208
3 changed files with 59 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
vllm-serve/templates/lws.yaml
View File

@ -31,19 +31,31 @@ spec:
DEST_DIR="{{ .Values.model.localMountPath }}/Weight/$MODEL_NAME"
# DEST_DIR="{{ .Values.model.localMountPath }}/{{ .Values.model.huggingfaceName }}"
# 检查模型是否存在，不存在则下载
echo "DEST_DIR= $DEST_DIR"
if [ ! -f "$DEST_DIR/config.json" ]; then
ls -l {{ .Values.model.localMountPath }}
echo "Downloading model {{ .Values.model.huggingfaceName }} to $DEST_DIR"
wget https://hf-mirror.com/hfd/hfd.sh
chmod a+x hfd.sh
apt update && apt upgrade
apt install aria2 -y
./hfd.sh {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
# huggingface-cli download {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
else
echo "Model already exists at $DEST_DIR"
# echo "DEST_DIR= $DEST_DIR"
# if [ ! -f "$DEST_DIR/config.json" ]; then
# ls -l {{ .Values.model.localMountPath }}
# echo "Downloading model {{ .Values.model.huggingfaceName }} to $DEST_DIR"
# wget https://hf-mirror.com/hfd/hfd.sh
# chmod a+x hfd.sh
# apt update && apt upgrade
# apt install aria2 -y
# ./hfd.sh {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
# # huggingface-cli download {{ .Values.model.huggingfaceName }} --local-dir "$DEST_DIR"
# else
# echo "Model already exists at $DEST_DIR"
# fi
SUCCESS_FLAG="${DEST_DIR}/.success_flag"
if [ -f "$SUCCESS_FLAG" ]; then
echo "✅ Success flag found. Skipping download."
exit 0
fi
echo "⬇️ Starting download..."
apk add --no-cache bash aria2 wget ca-certificates
wget https://hf-mirror.com/hfd/hfd.sh -O hfd.sh && chmod +x hfd.sh
./hfd.sh {{ .Values.model.huggingfaceName }} --tool aria2c -x 8 --local-dir "$DEST_DIR"
touch "$SUCCESS_FLAG"
echo "🎉 Done."
volumeMounts:
- name: weight-volume
mountPath: {{ .Values.model.localMountPath }}
@ -94,9 +106,9 @@ spec:
- containerPort: 8000
name: http
readinessProbe:
tcpSocket:
#httpGet:
#path: /health
# tcpSocket:
httpGet:
path: /health
port: 8000
initialDelaySeconds: 120
periodSeconds: 20
@ -190,4 +202,4 @@ spec:
tolerations:
{{- toYaml . | nindent 10 }}
{{- end }}
{{- end }}
{{- end }}