fix: fix bugs for initContainer in LWS

Update values.schema.json to add numerous new model names for enhanced support
Update vllm-serve/templates/single.yaml
2025-12-02 16:37:57 +08:00 · 2025-12-02 08:35:12 +00:00 · 2025-12-02 07:55:47 +00:00 · 2025-12-02 07:49:00 +00:00 · 2025-12-02 15:46:55 +08:00 · 2025-12-02 15:43:05 +08:00
5 changed files with 197 additions and 36 deletions
--- a/charts.list
+++ b/charts.list
@ -1,4 +1,4 @@
 # List each Helm chart directory to package and push (one per line)
-# vllm-serve
+vllm-serve
 # code-server-chart
-open-webui
+# open-webui
--- a/vllm-serve/Chart.yaml
+++ b/vllm-serve/Chart.yaml
@ -5,4 +5,4 @@ appVersion: 1.16.0
 description: A Helm chart for deploying vLLM with NFS storage
 name: vllm-serve
 type: application
-version: 0.2.0
+version: 0.2.1
--- a/vllm-serve/templates/lws.yaml
+++ b/vllm-serve/templates/lws.yaml
@ -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 "$SUCCESS_FLAG" ]; then
+                echo "✅ Success flag found. Skipping download."
+                exit 0
              fi
+              echo "⬇️ Starting download..."
+              apk add --no-cache bash aria2 wget ca-certificates curl
+              wget https://hf-mirror.com/hfd/hfd.sh -O hfd.sh && chmod +x hfd.sh
+              ./hfd.sh {{ .Values.model.huggingfaceName }} --tool aria2c -x 8 --local-dir "$DEST_DIR"
+
+              touch "$SUCCESS_FLAG"
+              echo "🎉 Done."
          volumeMounts:
          - name: weight-volume
            mountPath: {{ .Values.model.localMountPath }}
@ -94,9 +106,9 @@ spec:
              - containerPort: 8000
                name: http
            readinessProbe:
-              tcpSocket:
-                #httpGet:
-                #path: /health
+              # tcpSocket:
+              httpGet:
+                path: /health
                port: 8000
              initialDelaySeconds: 120
              periodSeconds: 20
@ -190,4 +202,4 @@ spec:
        tolerations:
          {{- toYaml . | nindent 10 }}
        {{- end }} 
-{{- end }}
+{{- end }}
--- a/vllm-serve/templates/single.yaml
+++ b/vllm-serve/templates/single.yaml
@ -16,7 +16,7 @@ spec:
      initContainers:
     # 模型下载作为第一个 initContainer
      - name: download-model
-        image: {{ .Values.model.download.image }}
+        image: alpine:latest
        imagePullPolicy: IfNotPresent
        env:
          - name: HF_ENDPOINT
@ -24,33 +24,46 @@ spec:
          - name: HUGGING_FACE_HUB_TOKEN
            value: {{ .Values.model.huggingfaceToken }}
        command:
-          - sh
+          - /bin/sh
          - -c
          - |
+            set -e
            MODEL_NAME=$(basename "{{ .Values.model.huggingfaceName }}")
            DEST_DIR="{{ .Values.model.localMountPath }}/Weight/$MODEL_NAME"
+            SUCCESS_FLAG="${DEST_DIR}/.success_flag"
            # 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 $DEST_DIR"
+            # fi
+            if [ -f "$SUCCESS_FLAG" ]; then
+              echo "✅ Success flag found. Skipping download."
+              exit 0
            fi
+            echo "⬇️ Starting download..."
+            apk add --no-cache bash aria2 wget ca-certificates curl
+            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 }}
      containers:
      - name: vllm-pod
        image: {{ .Values.vllm.image }}
-        imagePullPolicy:  IfNotPresent
+        imagePullPolicy:  {{ .Values.imagePullPolicy }}
        env:
        - name: HUGGING_FACE_HUB_TOKEN
          value: {{ .Values.vllm.huggingfaceToken }}
@ -81,6 +94,7 @@ spec:
            nvidia.com/gpu: "{{ .Values.resources.gpuLimit }}"
            memory: {{ .Values.resources.memoryLimit }}
            ephemeral-storage: 10Gi
+            cpu: {{ .Values.resources.cpuRequest }}
          requests:
            ephemeral-storage: 10Gi
            cpu: {{ .Values.resources.cpuRequest }}
@ -124,4 +138,4 @@ spec:
      tolerations:
        {{- toYaml . | nindent 8 }}
      {{- end }}
-{{- end }}
+{{- end }}
--- a/vllm-serve/values.schema.json
+++ b/vllm-serve/values.schema.json
@ -440,7 +440,142 @@
            "tencent/DRIVE-RL",
            "tencent/DRIVE-SFT",
            "Qwen/Qwen2.5-14B",
-            "BAAI/bge-base-zh-v1.5"
+            "BAAI/bge-base-zh-v1.5",
+            "01-ai/Yi-1.5-34B",
+            "01-ai/Yi-1.5-6B",
+            "01-ai/Yi-1.5-9B",
+            "01-ai/Yi-34B-Chat",
+            "ByteDance/Dolphin-1.5",
+            "ByteDance/Ouro-1.4B",
+            "ByteDance/Ouro-1.4B-Thinking",
+            "ByteDance/Ouro-2.6B",
+            "ByteDance/Ouro-2.6B-Thinking",
+            "OpenGVLab/InternVL3-38B",
+            "OpenGVLab/InternVL3-78B",
+            "OpenGVLab/InternVL3_5-1B",
+            "OpenGVLab/InternVL3_5-30B-A3B-Instruct",
+            "OpenGVLab/InternVL3_5-38B",
+            "OpenGVLab/InternVL3_5-8B",
+            "OpenGVLab/InternVL3_5-GPT-OSS-20B-A4B-Preview",
+            "OpenGVLab/Mini-InternVL2-2B-DA-Medical",
+            "OpenGVLab/SDLM-32B-D4",
+            "Qwen/CodeQwen1.5-7B-Chat",
+            "Qwen/Qwen1.5-1.8B",
+            "Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4",
+            "Qwen/Qwen2-0.5B",
+            "Qwen/Qwen2-Math-72B-Instruct",
+            "Qwen/Qwen2.5-0.5B",
+            "Qwen/Qwen2.5-1.5B",
+            "Qwen/Qwen2.5-1.5B-Instruct",
+            "Qwen/Qwen2.5-1.5B-Instruct-GGUF",
+            "Qwen/Qwen2.5-14B-Instruct",
+            "Qwen/Qwen2.5-14B-Instruct-1M",
+            "Qwen/Qwen2.5-32B-Instruct",
+            "Qwen/Qwen2.5-32B-Instruct-AWQ",
+            "Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4",
+            "Qwen/Qwen2.5-3B-Instruct",
+            "Qwen/Qwen2.5-3B-Instruct-GGUF",
+            "Qwen/Qwen2.5-72B-Instruct",
+            "Qwen/Qwen2.5-7B",
+            "Qwen/Qwen2.5-7B-Instruct",
+            "Qwen/Qwen2.5-7B-Instruct-1M",
+            "Qwen/Qwen2.5-7B-Instruct-GGUF",
+            "Qwen/Qwen2.5-Coder-0.5B",
+            "Qwen/Qwen2.5-Coder-1.5B",
+            "Qwen/Qwen2.5-Coder-1.5B-Instruct",
+            "Qwen/Qwen2.5-Coder-14B-Instruct",
+            "Qwen/Qwen2.5-Coder-32B-Instruct",
+            "Qwen/Qwen2.5-Coder-3B-Instruct-GGUF",
+            "Qwen/Qwen2.5-Coder-7B-Instruct",
+            "Qwen/Qwen2.5-Coder-7B-Instruct-GGUF",
+            "Qwen/Qwen2.5-Math-72B",
+            "Qwen/Qwen2.5-Math-7B",
+            "Qwen/Qwen2.5-VL-32B-Instruct",
+            "Qwen/Qwen2.5-VL-72B-Instruct-AWQ",
+            "Qwen/Qwen2.5-VL-7B-Instruct",
+            "Qwen/Qwen3-0.6B",
+            "Qwen/Qwen3-0.6B-Base",
+            "Qwen/Qwen3-1.7B",
+            "Qwen/Qwen3-1.7B-FP8",
+            "Qwen/Qwen3-14B-FP8",
+            "Qwen/Qwen3-14B-GGUF",
+            "Qwen/Qwen3-30B-A3B-Base",
+            "Qwen/Qwen3-30B-A3B-Thinking-2507-FP8",
+            "Qwen/Qwen3-Next-80B-A3B-Thinking-FP8",
+            "Qwen/Qwen3-VL-4B-Instruct-FP8",
+            "baichuan-inc/Baichuan-M2-32B-GPTQ-Int4",
+            "baidu/ERNIE-4.5-0.3B-Base-PT",
+            "baidu/ERNIE-4.5-21B-A3B-Base-PT",
+            "baidu/ERNIE-4.5-VL-28B-A3B-Base-PT",
+            "baidu/ERNIE-4.5-VL-28B-A3B-Thinking",
+            "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT",
+            "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
+            "deepseek-ai/DeepSeek-V3.1-Terminus",
+            "deepseek-ai/DeepSeek-V3.2-Exp",
+            "deepseek-ai/deepseek-coder-1.3b-base",
+            "deepseek-ai/deepseek-coder-1.3b-instruct",
+            "deepseek-ai/deepseek-coder-6.7b-instruct",
+            "google/codegemma-1.1-2b-GGUF",
+            "google/gemma-3-27b-pt",
+            "google/paligemma2-28b-pt-896",
+            "google/reformer-crime-and-punishment",
+            "google/reformer-enwik8",
+            "google/t5-11b-ssm-nq",
+            "google/t5-3b-ssm-nq",
+            "google/t5-large-ssm-nq",
+            "google/t5-small-ssm-nq",
+            "google/t5-xl-ssm-nq",
+            "google/t5-xxl-ssm-nq",
+            "google/t5gemma-ml-ml-ul2-it",
+            "internlm/Spatial-SSRL-7B",
+            "llava-hf/llava-1.5-13b-hf",
+            "llava-hf/llava-v1.6-34b-hf",
+            "meta-llama/Llama-3.1-405B",
+            "meta-llama/Llama-3.1-405B-Instruct",
+            "meta-llama/Llama-3.1-70B",
+            "meta-llama/Llama-3.1-70B-Instruct",
+            "meta-llama/Llama-3.1-8B",
+            "meta-llama/Llama-3.1-8B-Instruct",
+            "meta-llama/Llama-3.2-11B-Vision-Instruct",
+            "meta-llama/Llama-3.2-1B",
+            "meta-llama/Llama-3.2-1B-Instruct",
+            "meta-llama/Llama-3.2-3B",
+            "meta-llama/Llama-3.2-3B-Instruct",
+            "meta-llama/Llama-3.2-90B-Vision",
+            "meta-llama/Llama-3.2-90B-Vision-Instruct",
+            "meta-llama/Llama-3.3-70B-Instruct",
+            "microsoft/MediPhi-Instruct",
+            "microsoft/Phi-3-medium-4k-instruct-onnx-cpu",
+            "microsoft/Phi-3.5-mini-instruct",
+            "microsoft/bitnet-b1.58-2B-4T",
+            "microsoft/bitnet-b1.58-2B-4T-gguf",
+            "microsoft/kosmos-2.5",
+            "microsoft/kosmos-2.5-chat",
+            "microsoft/llava-med-v1.5-mistral-7b",
+            "mistralai/Mistral-7B-Instruct-v0.2",
+            "moonshotai/Kimi-Dev-72B",
+            "moonshotai/Kimi-K2-Base",
+            "moonshotai/Kimi-K2-Instruct",
+            "moonshotai/Kimi-K2-Instruct-0905",
+            "moonshotai/Kimi-K2-Thinking",
+            "moonshotai/Kimi-Linear-48B-A3B-Base",
+            "moonshotai/Kimi-Linear-48B-A3B-Instruct",
+            "moonshotai/Moonlight-16B-A3B",
+            "openbmb/MiniCPM4.1-8B",
+            "tencent/DeepSeek-V3.1-Terminus-W4AFP8",
+            "tencent/Hunyuan-0.5B-Pretrain",
+            "zai-org/GLM-4-9B-0414",
+            "zai-org/GLM-4.1V-9B-Base",
+            "zai-org/GLM-4.5-Air",
+            "zai-org/GLM-4.5V-FP8",
+            "zai-org/GLM-4.6",
+            "zai-org/GLM-4.6-FP8",
+            "zai-org/GLM-Z1-32B-0414",
+            "zai-org/GLM-Z1-9B-0414",
+            "zai-org/Glyph",
+            "zai-org/UI2Code_N",
+            "zai-org/WebVIA-Agent",
+            "zai-org/codegeex4-all-9b"
          ]
        }
      },
Author	SHA1	Message	Date
Ivan087	69da2b8c5b	fix: fix bugs for initContainer in LWS	2025-12-02 16:37:57 +08:00
mangomqy	4e9a086547	Update values.schema.json to add numerous new model names for enhanced support All checks were successful Publish Helm Charts / helm-publish (push) Successful in 7s Details	2025-12-02 08:35:12 +00:00
ivanwu	5aebfc5cdf	Update vllm-serve/templates/single.yaml All checks were successful Publish Helm Charts / helm-publish (push) Successful in 7s Details	2025-12-02 07:55:47 +00:00
ivanwu	210c967135	Merge pull request 'fix: bugs for interuption of downloading models' (#2 ) from vllm into main All checks were successful Publish Helm Charts / helm-publish (push) Successful in 25s Details Reviewed-on: #2	2025-12-02 07:49:00 +00:00
Ivan087	9e08afdcb2	build oci for vllm 0.3.1	2025-12-02 15:46:55 +08:00
Ivan087	fccbb10208	fix: bugs for interuption of downloading model	2025-12-02 15:43:05 +08:00