feat: GRPO CLI 接入 + on-policy，OpenAI API top_k 参数化，补充训练参数表

- train.py 新增 --train_type=grpo 及参数 (--grpo_clip_eps, --grpo_kl_coef, --group_size, --grpo_sync_interval, --start_epoch)
- GRPOStrategy 统一 on-policy 模式，ratio = exp(logπ_θ - logπ_ref)，PPO 裁剪目标，sync_interval 自动同步 ref_model
- ChatCompletionRequest 新增 top_k 参数，不再硬编码
- 补充 README 完整训练参数表（含此前缺失的 max_grad_norm / adamw / window_size / stride 等）

astrai/inference/server.py

@@ -51,6 +51,7 @@ class ChatCompletionRequest(BaseModel):
     messages: List[ChatMessage]
     temperature: Optional[float] = Field(default=1.0, ge=0.0, le=2.0)
     top_p: Optional[float] = Field(default=1.0, ge=0.0, le=1.0)
+    top_k: Optional[int] = Field(default=50, ge=1)
     stream: Optional[bool] = False
     stop: Optional[Union[str, List[str]]] = None
     max_tokens: Optional[int] = Field(default=2048, ge=1)
@@ -204,7 +205,7 @@ async def chat_completion(request: ChatCompletionRequest):
             max_tokens=request.max_tokens,
             temperature=request.temperature,
             top_p=request.top_p,
-            top_k=50,
+            top_k=request.top_k,
         )
 
         async def event_stream():
@@ -256,7 +257,7 @@ async def chat_completion(request: ChatCompletionRequest):
         max_tokens=request.max_tokens,
         temperature=request.temperature,
         top_p=request.top_p,
-        top_k=50,
+        top_k=request.top_k,
     )
     async for token in agen:
         chunks.append(token)