fix: 修复 remove_task 未释放 KV cache slot 导致第二轮对话死锁

- remove_task() 现在释放 KV cache slot 和 prefix cache 引用
- _refill_active_batch 中 alloc 失败时将剩余 task 推回 waiting_queue
- 主循环增加 try/except 异常兜底,发送 _STOP 给所有 task
- 重构:server.py 全局变量改为 ServerState 类;automodel.py
  使用 Registry 替代裸 dict;合并 TrainContextBuilder 的 with_*
  方法到 build()
This commit is contained in:
2026-05-08 14:53:04 +08:00
parent ffff05b2c6
commit a6f5ff3b37
8 changed files with 165 additions and 142 deletions
+1 -5
View File
@@ -35,11 +35,7 @@ class Trainer:
def _build_context(self, checkpoint: Optional[Checkpoint]) -> TrainContext:
return (
TrainContextBuilder(self.train_config)
.with_checkpoint(checkpoint)
.with_dataloader()
.with_strategy()
.build()
TrainContextBuilder(self.train_config).with_checkpoint(checkpoint).build()
)
def _call_callbacks(self, method_name: str, context: TrainContext):