[FEAT] Support fast engine recovery through weight cache (#27139)

Signed-off-by: Michael Qiu <qiudayu.qdy@antgroup.com>
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
This commit is contained in:
Mike Qiu
2026-07-25 14:31:21 +08:00
committed by GitHub
co-authored by liusy58 Alex Nails
parent bdd0698541
commit f9c14e6bd4
18 changed files with 3404 additions and 2 deletions
@@ -2675,6 +2675,7 @@ def launch_server(
port_args,
scheduler_init_result,
subprocess_watchdog,
_weight_cache_daemon_procs,
) = Engine._launch_subprocesses(
server_args=server_args,
init_tokenizer_manager_func=init_tokenizer_manager_func,