start_services.sh

#!/bin/bash
set -euo pipefail

# 配置
MODEL_REPO="${MODEL_REPO:-stepfun-ai/Step-Audio-R1}"
MODEL_DIR="${MODEL_DIR:-/tmp/models/Step-Audio-R1}"
API_PORT="${API_PORT:-9999}"
GRADIO_PORT="${GRADIO_PORT:-7860}"

echo "Starting Step Audio R1 services..."
echo "Model: $MODEL_REPO"
echo "Model Dir: $MODEL_DIR"
echo "API Port: $API_PORT"

# 下载模型（如果需要）
if [[ ! -d "$MODEL_DIR" ]] || [[ ! -f "$MODEL_DIR/config.json" ]]; then
    echo "Downloading model to: $MODEL_DIR"
    mkdir -p "$MODEL_DIR"

    if command -v hf &> /dev/null; then
        hf download "$MODEL_REPO" --local-dir "$MODEL_DIR"
    elif command -v huggingface-cli &> /dev/null; then
        huggingface-cli download "$MODEL_REPO" --local-dir "$MODEL_DIR" --local-dir-use-symlinks False
    else
        echo "Neither hf nor huggingface-cli found. Skipping download."
        exit 1
    fi

    echo "✓ Model downloaded"
else
    echo "✓ Model already exists locally"
fi

# # Step-Audio-R1 的 chat template
# CHAT_TEMPLATE='{%- macro render_content(content) -%}{%- if content is string -%}{{- content.replace("<audio_patch>\\n", "<audio_patch>") -}}{%- elif content is mapping -%}{{- content["'"'"'value'"'"'] if '"'"'value'"'"' in content else content["'"'"'text'"'"'] -}}{%- elif content is iterable -%}{%- for item in content -%}{%- if item.type == '"'"'text'"'"' -%}{{- item["'"'"'value'"'"'] if '"'"'value'"'"' in item else item["'"'"'text'"'"'] -}}{%- elif item.type == '"'"'audio'"'"' -%}<audio_patch>{%- endif -%}{%- endfor -%}{%- endif -%}{%- endmacro -%}{%- if tools -%}{{- '"'"'<|BOT|>system\\n'"'"' -}}{%- if messages[0]["'"'"'role'"'"'] == '"'"'system'"'"' -%}{{- render_content(messages[0]["'"'"'content'"'"']) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{{- '"'"'<|BOT|>tool_json_schemas\\n'"'"' + tools|tojson + '"'"'<|EOT|>'"'"' -}}{%- else -%}{%- if messages[0]["'"'"'role'"'"'] == '"'"'system'"'"' -%}{{- '"'"'<|BOT|>system\\n'"'"' + render_content(messages[0]["'"'"'content'"'"']) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- endif -%}{%- for message in messages -%}{%- if message["role"] == "user" -%}{{- '"'"'<|BOT|>human\\n'"'"' + render_content(message["content"]) + '"'"'<|EOT|>'"'"' -}}{%- elif message["role"] == "assistant" -%}{{- '"'"'<|BOT|>assistant\\n'"'"' + (render_content(message["content"]) if message["content"] else '"'"''"'"') -}}{%- set is_last_assistant = true -%}{%- for m in messages[loop.index:] -%}{%- if m["role"] == "assistant" -%}{%- set is_last_assistant = false -%}{%- endif -%}{%- endfor -%}{%- if not is_last_assistant -%}{{- '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- elif message["role"] == "function_output" -%}{%- else -%}{%- if not (loop.first and message["role"] == "system") -%}{{- '"'"'<|BOT|>'"'"' + message["role"] + '"'"'\\n'"'"' + render_content(message["content"]) + '"'"'<|EOT|>'"'"' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{- '"'"'<|BOT|>assistant\\n'"'"' -}}{%- endif -%}'

# echo "starting vllm server"

# # 后台启动 vLLM API
# python3 -m vllm.entrypoints.openai.api_server \
#     --model "$MODEL_DIR" \
#     --port "$API_PORT" \
#     --host 0.0.0.0 \
#     --max-model-len 65536 \
#     --tensor-parallel-size 4 \
#     --gpu-memory-utilization 0.85 \
#     --trust-remote-code \
#     --interleave-mm-strings \
#     --chat-template "$CHAT_TEMPLATE" \
#     &

# VLLM_PID=$!
# echo "vLLM started (PID: $VLLM_PID)"


# 启动 Gradio (前台运行)
export API_BASE_URL="http://localhost:$API_PORT/v1"
export MODEL_NAME="Step-Audio-R1"

python3 app.py --host 0.0.0.0 --port "$GRADIO_PORT"

# 清理
# trap 'kill $VLLM_PID' EXIT