diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..a059664
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,10 @@
+.git
+.gitignore
+__pycache__
+.pytest_cache
+.venv
+*.pyc
+*.pyo
+*.pyd
+*.log
+README.md
diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..0aabe69
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,12 @@
+MODEL_NAME=Qwen/Qwen3-14B
+HOST=0.0.0.0
+PORT=8000
+TENSOR_PARALLEL_SIZE=2
+GPU_MEMORY_UTILIZATION=0.92
+MAX_MODEL_LEN=8192
+MAX_NUM_SEQS=64
+DTYPE=bfloat16
+ENFORCE_EAGER=false
+TRUST_REMOTE_CODE=false
+REVISION=
+API_KEY=
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..c37fb40
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,23 @@
+FROM rocm/vllm:rocm7.12.0_gfx120X-all_ubuntu24.04_py3.12_pytorch_2.9.1_vllm_0.16.0
+
+WORKDIR /workspace
+
+COPY requirements.txt /workspace/requirements.txt
+RUN pip install --no-cache-dir -r /workspace/requirements.txt
+
+COPY app /workspace/app
+
+ENV PYTHONUNBUFFERED=1
+ENV HOST=0.0.0.0
+ENV PORT=8000
+ENV TENSOR_PARALLEL_SIZE=2
+ENV GPU_MEMORY_UTILIZATION=0.92
+ENV MAX_MODEL_LEN=8192
+ENV MAX_NUM_SEQS=64
+ENV DTYPE=bfloat16
+ENV ENFORCE_EAGER=false
+ENV TRUST_REMOTE_CODE=false
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
diff --git a/README.md b/README.md
index 1f9fb62..146e72f 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,99 @@
-# rocm_vllm_nightly
+# ROCm vLLM 容器化推理项目
+
+基于镜像 `rocm/vllm:rocm7.12.0_gfx120X-all_ubuntu24.04_py3.12_pytorch_2.9.1_vllm_0.16.0` 的 Python 推理服务，适配双 AMD R9700 32G GPU。
+
+## 项目目标
+
+- 提供可容器化部署的模型推理 API
+- 使用 vLLM 在双 GPU 上进行张量并行推理
+- 提供健康检查、鉴权和参数化配置能力
+
+## 目录结构
+
+```text
+.
+├── app
+│   ├── config.py
+│   ├── engine.py
+│   ├── main.py
+│   └── schemas.py
+├── .dockerignore
+├── .env.example
+├── docker-compose.yml
+├── Dockerfile
+└── requirements.txt
+```
+
+## 接口说明
+
+### 1) 健康检查
+
+- 方法：`GET /health`
+- 返回：服务状态与当前模型名
+
+### 2) 文本生成
+
+- 方法：`POST /v1/generate`
+- Header：可选 `x-api-key`（配置 `API_KEY` 后必填）
+- 请求体：
+
+```json
+{
+  "prompt": "请介绍一下ROCm和vLLM的关系",
+  "max_tokens": 256,
+  "temperature": 0.7,
+  "top_p": 0.95,
+  "repetition_penalty": 1.0,
+  "stop": ["</s>"]
+}
+```
+
+## 配置项
+
+可通过 `.env` 配置，建议先复制 `.env.example`：
+
+- `MODEL_NAME`：模型名称或本地路径
+- `TENSOR_PARALLEL_SIZE`：张量并行数，双卡建议为 `2`
+- `GPU_MEMORY_UTILIZATION`：单卡显存利用率，建议 `0.90~0.95`
+- `MAX_MODEL_LEN`：模型最大上下文长度
+- `MAX_NUM_SEQS`：并发序列数量
+- `DTYPE`：精度类型，默认 `bfloat16`
+- `API_KEY`：可选接口访问密钥
+
+## 部署步骤
+
+1. 准备环境变量：
+
+```bash
+cp .env.example .env
+```
+
+2. 修改 `.env` 中的 `MODEL_NAME` 与资源参数。
+
+3. 构建并启动容器：
+
+```bash
+docker compose up -d --build
+```
+
+4. 验证服务：
+
+```bash
+curl http://localhost:8000/health
+```
+
+## 推理请求示例
+
+```bash
+curl -X POST "http://localhost:8000/v1/generate" \
+  -H "Content-Type: application/json" \
+  -d "{\"prompt\":\"请用三句话介绍大模型推理优化\",\"max_tokens\":128,\"temperature\":0.7}"
+```
+
+## 双 AMD R9700 调优建议
+
+- 首选 `TENSOR_PARALLEL_SIZE=2`
+- 首次部署建议设置 `GPU_MEMORY_UTILIZATION=0.90`，稳定后再调高
+- 若模型较大且吞吐压力高，可逐步调低 `MAX_MODEL_LEN` 或 `MAX_NUM_SEQS`
+- 确保宿主机已正确安装 ROCm 驱动并暴露 `/dev/kfd` 与 `/dev/dri`
 
diff --git a/app/config.py b/app/config.py
new file mode 100644
index 0000000..5b9bb9d
--- /dev/null
+++ b/app/config.py
@@ -0,0 +1,45 @@
+from functools import lru_cache
+import os
+from typing import Optional
+
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+from app.model_catalog import resolve_model_profile
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8")
+
+    config_file: str = Field(default="config.json", alias="MODEL_CONFIG_FILE")
+    model_key: Optional[str] = Field(default=None, alias="MODEL_KEY")
+    selected_model: Optional[str] = None
+    model_name: str = Field(default="", alias="MODEL_NAME")
+    served_model_name: Optional[str] = None
+    host: str = Field(default="0.0.0.0", alias="HOST")
+    port: int = Field(default=8000, alias="PORT")
+    max_model_len: int = Field(default=8192, alias="MAX_MODEL_LEN")
+    gpu_memory_utilization: float = Field(default=0.92, alias="GPU_MEMORY_UTILIZATION")
+    tensor_parallel_size: int = Field(default=2, alias="TENSOR_PARALLEL_SIZE")
+    max_num_seqs: int = Field(default=64, alias="MAX_NUM_SEQS")
+    max_tokens: int = Field(default=4096, alias="MAX_TOKENS")
+    dtype: str = Field(default="bfloat16", alias="DTYPE")
+    enforce_eager: bool = Field(default=False, alias="ENFORCE_EAGER")
+    trust_remote_code: bool = Field(default=False, alias="TRUST_REMOTE_CODE")
+    tool_call_parser: Optional[str] = Field(default=None, alias="TOOL_CALL_PARSER")
+    enable_auto_tool_choice: bool = Field(default=False, alias="ENABLE_AUTO_TOOL_CHOICE")
+    revision: Optional[str] = Field(default=None, alias="REVISION")
+    api_key: Optional[str] = Field(default=None, alias="API_KEY")
+
+
+@lru_cache(maxsize=1)
+def get_settings() -> Settings:
+    settings = Settings()
+    _, updates, env_vars = resolve_model_profile(
+        catalog_path=settings.config_file,
+        requested_model=settings.model_key,
+        requested_tp=settings.tensor_parallel_size,
+    )
+    for key, value in env_vars.items():
+        os.environ[key] = value
+    return settings.model_copy(update=updates)
diff --git a/app/engine.py b/app/engine.py
new file mode 100644
index 0000000..2916320
--- /dev/null
+++ b/app/engine.py
@@ -0,0 +1,46 @@
+from threading import Lock
+
+from vllm import LLM, SamplingParams
+
+from app.config import Settings
+from app.schemas import GenerateRequest, GenerateResponse
+
+
+class InferenceEngine:
+    def __init__(self, settings: Settings) -> None:
+        self.settings = settings
+        self.lock = Lock()
+        self.model = LLM(
+            model=settings.model_name,
+            tensor_parallel_size=settings.tensor_parallel_size,
+            max_model_len=settings.max_model_len,
+            gpu_memory_utilization=settings.gpu_memory_utilization,
+            max_num_seqs=settings.max_num_seqs,
+            dtype=settings.dtype,
+            enforce_eager=settings.enforce_eager,
+            trust_remote_code=settings.trust_remote_code,
+            revision=settings.revision,
+        )
+
+    def generate(self, req: GenerateRequest) -> GenerateResponse:
+        sampling_params = SamplingParams(
+            temperature=req.temperature,
+            top_p=req.top_p,
+            max_tokens=req.max_tokens,
+            repetition_penalty=req.repetition_penalty,
+            stop=req.stop,
+        )
+        with self.lock:
+            outputs = self.model.generate([req.prompt], sampling_params, use_tqdm=False)
+        output = outputs[0]
+        completion = output.outputs[0].text
+        usage_prompt = len(output.prompt_token_ids)
+        usage_completion = len(output.outputs[0].token_ids)
+        return GenerateResponse(
+            text=completion,
+            prompt=req.prompt,
+            model=self.settings.model_name,
+            usage_prompt_tokens=usage_prompt,
+            usage_completion_tokens=usage_completion,
+            usage_total_tokens=usage_prompt + usage_completion,
+        )
diff --git a/app/main.py b/app/main.py
new file mode 100644
index 0000000..4fef1b3
--- /dev/null
+++ b/app/main.py
@@ -0,0 +1,43 @@
+from contextlib import asynccontextmanager
+
+from fastapi import Depends, FastAPI, Header, HTTPException, status
+
+from app.config import Settings, get_settings
+from app.engine import InferenceEngine
+from app.schemas import GenerateRequest, GenerateResponse, HealthResponse
+
+engine: InferenceEngine | None = None
+
+
+def verify_api_key(
+    settings: Settings = Depends(get_settings), x_api_key: str | None = Header(default=None)
+) -> None:
+    if settings.api_key and x_api_key != settings.api_key:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail="Invalid API key",
+        )
+
+
+@asynccontextmanager
+async def lifespan(_: FastAPI):
+    global engine
+    settings = get_settings()
+    engine = InferenceEngine(settings)
+    yield
+    engine = None
+
+
+app = FastAPI(title="ROCm vLLM Inference API", version="1.0.0", lifespan=lifespan)
+
+
+@app.get("/health", response_model=HealthResponse)
+def health(settings: Settings = Depends(get_settings)) -> HealthResponse:
+    return HealthResponse(status="ok", model=settings.model_name)
+
+
+@app.post("/v1/generate", response_model=GenerateResponse, dependencies=[Depends(verify_api_key)])
+def generate(req: GenerateRequest) -> GenerateResponse:
+    if engine is None:
+        raise HTTPException(status_code=status.HTTP_503_SERVICE_UNAVAILABLE, detail="Engine not ready")
+    return engine.generate(req)
diff --git a/app/model_catalog.py b/app/model_catalog.py
new file mode 100644
index 0000000..08d827f
--- /dev/null
+++ b/app/model_catalog.py
@@ -0,0 +1,66 @@
+import json
+from pathlib import Path
+from typing import Any
+
+
+def _to_bool(value: Any, default: bool) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        normalized = value.strip().lower()
+        if normalized in {"true", "1", "yes", "y"}:
+            return True
+        if normalized in {"false", "0", "no", "n"}:
+            return False
+    return default
+
+
+def _to_int(value: Any, default: int) -> int:
+    try:
+        return int(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def _to_float(value: Any, default: float) -> float:
+    try:
+        return float(value)
+    except (TypeError, ValueError):
+        return default
+
+
+def resolve_model_profile(
+    catalog_path: str, requested_model: str | None, requested_tp: int
+) -> tuple[str, dict[str, Any], dict[str, str]]:
+    content = json.loads(Path(catalog_path).read_text(encoding="utf-8"))
+    if not isinstance(content, dict):
+        raise ValueError("config.json must be a JSON object")
+    default_model = content.get("default_model")
+    profiles = {k: v for k, v in content.items() if k != "default_model"}
+    model_key = requested_model or default_model
+    if not model_key or model_key not in profiles:
+        raise ValueError(f"model profile '{model_key}' not found in config.json")
+    profile = profiles[model_key]
+    if not isinstance(profile, dict):
+        raise ValueError(f"model profile '{model_key}' must be a JSON object")
+    valid_tp_raw = profile.get("valid_tp", [])
+    valid_tp = [_to_int(item, 0) for item in valid_tp_raw if _to_int(item, 0) > 0]
+    resolved_tp = requested_tp
+    if valid_tp and resolved_tp not in valid_tp:
+        resolved_tp = valid_tp[0]
+    updates = {
+        "selected_model": model_key,
+        "model_name": profile.get("hf_model_id", model_key),
+        "served_model_name": profile.get("served_model_name", model_key),
+        "max_model_len": _to_int(profile.get("ctx"), 8192),
+        "max_num_seqs": _to_int(profile.get("max_num_seqs"), 64),
+        "max_tokens": _to_int(profile.get("max_tokens"), 4096),
+        "gpu_memory_utilization": _to_float(profile.get("gpu_util"), 0.92),
+        "trust_remote_code": _to_bool(profile.get("trust_remote"), False),
+        "enforce_eager": _to_bool(profile.get("enforce_eager"), False),
+        "tensor_parallel_size": resolved_tp,
+        "tool_call_parser": profile.get("tool_call_parser"),
+        "enable_auto_tool_choice": _to_bool(profile.get("enable_auto_tool_choice"), False),
+    }
+    env_vars = {str(k): str(v) for k, v in dict(profile.get("env", {})).items()}
+    return model_key, updates, env_vars
diff --git a/app/schemas.py b/app/schemas.py
new file mode 100644
index 0000000..16e0a8d
--- /dev/null
+++ b/app/schemas.py
@@ -0,0 +1,26 @@
+from typing import List, Optional
+
+from pydantic import BaseModel, Field
+
+
+class GenerateRequest(BaseModel):
+    prompt: str
+    max_tokens: int = Field(default=256, ge=1, le=4096)
+    temperature: float = Field(default=0.7, ge=0.0, le=2.0)
+    top_p: float = Field(default=0.95, gt=0.0, le=1.0)
+    repetition_penalty: float = Field(default=1.0, ge=0.5, le=2.0)
+    stop: Optional[List[str]] = None
+
+
+class GenerateResponse(BaseModel):
+    text: str
+    prompt: str
+    model: str
+    usage_prompt_tokens: int
+    usage_completion_tokens: int
+    usage_total_tokens: int
+
+
+class HealthResponse(BaseModel):
+    status: str
+    model: str
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..4fd9bdf
--- /dev/null
+++ b/config.json
@@ -0,0 +1,55 @@
+{
+  "default_model": "Qwen3.5-35B-A3B-GPTQ-Int4",
+  "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit": {
+    "ctx": "24576",
+    "trust_remote": true,
+    "valid_tp": [2],
+    "max_num_seqs": "32",
+    "max_tokens": "16384",
+    "gpu_util": "0.98",
+    "enforce_eager": false,
+    "env": {
+      "VLLM_USE_TRITON_AWQ": "1"
+    },
+    "tool_call_parser": "qwen3_xml",
+    "enable_auto_tool_choice": true,
+    "served_model_name": "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit",
+    "hf_model_id": "cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit"
+  },
+  "GLM-4.7-Flash-AWQ": {
+    "ctx": "32768",
+    "trust_remote": true,
+    "valid_tp": [1, 2],
+    "max_num_seqs": "64",
+    "max_tokens": "32768",
+    "gpu_util": "0.98",
+    "tool_call_parser": "qwen3_xml",
+    "enable_auto_tool_choice": true,
+    "served_model_name": "GLM-4.7-Flash-AWQ",
+    "hf_model_id": "THUDM/GLM-4.7-Flash-AWQ"
+  },
+  "Qwen3.5-27B-FP8": {
+    "ctx": "32768",
+    "trust_remote": true,
+    "valid_tp": [1, 2],
+    "max_num_seqs": "64",
+    "max_tokens": "32768",
+    "gpu_util": "0.98",
+    "tool_call_parser": "qwen3_xml",
+    "enable_auto_tool_choice": true,
+    "served_model_name": "Qwen3.5-27B-FP8",
+    "hf_model_id": "RedHatAI/Qwen3.5-27B-FP8-dynamic"
+  },
+  "Qwen3.5-35B-A3B-GPTQ-Int4": {
+    "ctx": "32768",
+    "trust_remote": true,
+    "valid_tp": [1, 2],
+    "max_num_seqs": "64",
+    "max_tokens": "32768",
+    "gpu_util": "0.98",
+    "tool_call_parser": "qwen3_xml",
+    "enable_auto_tool_choice": true,
+    "served_model_name": "Qwen3.5-35B-A3B-GPTQ-Int4",
+    "hf_model_id": "Qwen/Qwen3.5-35B-A3B-GPTQ-Int4"
+  }
+}
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..13fcd3f
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,24 @@
+services:
+  inference:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    image: rocm-vllm-inference:latest
+    container_name: rocm-vllm-inference
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env
+    devices:
+      - /dev/kfd
+      - /dev/dri
+    group_add:
+      - video
+      - render
+    ipc: host
+    shm_size: 16g
+    cap_add:
+      - SYS_PTRACE
+    security_opt:
+      - seccomp=unconfined
+    restart: unless-stopped
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..49a035e
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+fastapi==0.116.1
+uvicorn==0.35.0
+pydantic==2.11.7
+pydantic-settings==2.11.0