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
This commit is contained in:
2026-05-09 14:36:42 +08:00
parent bc7c82977e
commit 283bcaf2ff
12 changed files with 49 additions and 30 deletions
+11 -6
View File
@@ -56,6 +56,7 @@ class Task:
self.arrival_time = time.time()
self.finish_time: Optional[float] = None
self.stream_callback = stream_callback
self._pages_freed: bool = False
@property
def next_pos(self) -> int:
@@ -167,9 +168,11 @@ class InferenceScheduler:
self.active_tasks = [t for t in self.active_tasks if t.task_id != task_id]
for task in removed_active:
self._free_pages(task.page_table)
task.page_table.clear()
task.n_pages = 0
if not task._pages_freed:
self._free_pages(task.page_table)
task.page_table.clear()
task.n_pages = 0
task._pages_freed = True
def _free_pages(self, indices: List[int]) -> None:
for idx in indices:
@@ -185,9 +188,11 @@ class InferenceScheduler:
self._total_tokens += task.output_tokens
for task in finished:
self._free_pages(task.page_table)
task.page_table.clear()
task.n_pages = 0
if not task._pages_freed:
self._free_pages(task.page_table)
task.page_table.clear()
task.n_pages = 0
task._pages_freed = True
self.active_tasks = [
t for t in self.active_tasks if t.status != TaskStatus.FINISHED