Skip to content

Commit 809f25f

Browse files
committed
fix
1 parent 5942a62 commit 809f25f

File tree

1 file changed

+4
-0
lines changed
  • lightllm/server/router/model_infer/mode_backend/pd_nixl/prefill_node_impl

1 file changed

+4
-0
lines changed

lightllm/server/router/model_infer/mode_backend/pd_nixl/prefill_node_impl/prefill_impl.py

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -65,6 +65,10 @@ def _prefill_chuncked_handle_func(
6565
"""
6666
在每一步chuncked prefill 后,尝试生成chuncked 传输任务,发个 kv_move_manager 进行处理。
6767
"""
68+
# 系统内部的 health 请求不创建 kv 传输任务。
69+
if req_obj.req_id < 0:
70+
return
71+
6872
# 传输的 kv 要少一个,不然decode 无法有下一个输入推理出下一个token
6973
input_len = req_obj.shm_req.input_len - 1
7074
page_size = self.args.nixl_pd_kv_page_size

0 commit comments

Comments
 (0)