fix: 修复 CLI 参数缺失/重复、device_ids 越界、generate 参数名不一致、scheduler 时序、非流式截断等 bug

- train.py: 补上 --batch_size、--grpo_clip_eps，删除 3 处重复 --group_size
- generate.py: --model_dir 改为 --param_path 对齐 README
- automodel.py: from_pretrained 新增 strict 参数（默认 True）
- parallel/setup.py: 修复 device_ids 索引越界
- train_callback.py: scheduler.step() 移至 on_step_end
- test_train_strategy.py: 测试中补 optimizer.step()
- engine.py: 非流式改为循环等待所有任务完成，补 remove_task 清理
- scheduler.py: Task 添加 _pages_freed 标志，杜绝双重释放
- trainer.py: accumulation_steps=0 时 clamp 为 1
- tokenizer.py: save_pretrained 添加 _tokenizer is None 检查
- benchmark.py: 修复 ModelConfig 过时 import 路径
- inference/__init__.py: 修复 stale docstring

scripts/tools/benchmark.py

@@ -6,8 +6,9 @@ from typing import Any, Dict
 import torch
 from torch import Tensor
 
+from astrai.config import ModelConfig
 from astrai.inference.cache import PagedCache
-from astrai.model.transformer import ModelConfig, Transformer
+from astrai.model.transformer import Transformer
 
 
 @dataclass

scripts/tools/generate.py

@@ -9,7 +9,7 @@ from astrai.tokenize import AutoTokenizer
 
 
 def processor(
-    model_dir: str,
+    param_path: str,
     input_json_file: str,
     output_json_file: str,
     temperature: float,
@@ -20,8 +20,8 @@ def processor(
     max_tokens: int,
 ):
     # Load model and tokenizer
-    model = AutoModel.from_pretrained(model_dir)
-    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+    model = AutoModel.from_pretrained(param_path)
+    tokenizer = AutoTokenizer.from_pretrained(param_path)
     model.to(device="cuda", dtype=torch.bfloat16)
 
     # Create inference engine
@@ -72,7 +72,7 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Run generate with a Khaosz model.")
 
     parser.add_argument(
-        "--model_dir", type=str, required=True, help="Path to the model directory."
+        "--param_path", type=str, required=True, help="Path to the model directory."
     )
     parser.add_argument(
         "--input_json_file",

scripts/tools/train.py

@@ -42,7 +42,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--n_epoch", type=int, default=1, help="Number of epochs to train."
     )
-    parser.add_argument("--group_size", type=int, default=4, help="GRPO group size.")
+    parser.add_argument("--batch_size", type=int, default=1, help="Batch size per GPU.")
     parser.add_argument(
         "--accumulation_steps",
         type=int,
@@ -53,7 +53,7 @@ def parse_args() -> argparse.Namespace:
         "--warmup_steps",
         type=int,
         default=1000,
-        help="Number of iters between warnings.",
+        help="Number of warmup steps for LR scheduler.",
     )
     parser.add_argument(
         "--max_lr", type=float, default=3e-4, help="Max learning rate for training."
@@ -98,23 +98,19 @@ def parse_args() -> argparse.Namespace:
         "--window_size",
         type=int,
         default=None,
-        help="the max length of the input sequence.",
+        help="Max length of the input sequence.",
     )
     parser.add_argument(
-        "--stride", type=int, default=None, help="the step size of the input sequence."
+        "--stride", type=int, default=None, help="Step size of the input sequence."
     )
     parser.add_argument("--dpo_beta", type=float, default=0.1, help="DPO beta value.")
     parser.add_argument("--group_size", type=int, default=4, help="GRPO group size.")
     parser.add_argument(
-        "--on_policy",
-        action="store_true",
-        default=False,
-        help="Enable on-policy GRPO mode.",
+        "--grpo_clip_eps", type=float, default=0.2, help="GRPO clipping epsilon."
     )
     parser.add_argument(
         "--grpo_kl_coef", type=float, default=0.01, help="GRPO KL penalty coefficient."
     )
-    parser.add_argument("--group_size", type=int, default=4, help="GRPO group size.")
     parser.add_argument(
         "--label_smoothing",
         type=float,
@@ -134,7 +130,6 @@ def parse_args() -> argparse.Namespace:
         default="checkpoint",
         help="Directory to save checkpoints.",
     )
-    parser.add_argument("--group_size", type=int, default=4, help="GRPO group size.")
     parser.add_argument(
         "--grpo_sync_interval",
         type=int,