- astrai/inference/scheduler.py: add_task 增加 max_seq_len 检查,超限时直接发 STOP 信号终止 - astrai/inference/scheduler.py: _maybe_alloc_page 返回 bool,alloc 失败时标记 ABORTED + 发 STOP - astrai/inference/scheduler.py: _execute_decode 过滤分配失败任务,避免 page_table 越界 - astrai/inference/scheduler.py: _remove_finished_tasks 清理 ABORTED 任务并释放 pages - astrai/inference/scheduler.py: _execute_prefill input_mask 改为覆盖全部 prompt_len - astrai/model/transformer.py: seq_mask is None 分支补全 start_pos + seq_len 列 |
||
|---|---|---|
| .. | ||
| config | ||
| dataset | ||
| inference | ||
| model | ||
| parallel | ||
| tokenize | ||
| trainer | ||
| __init__.py | ||
| factory.py | ||
| serialization.py | ||