[Refactor] Cuda Graph Runner/Backend Refactor (#23906)
Co-authored-by: BBuf <1182563586@qq.com> Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com> Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
This commit is contained in:
co-authored by
BBuf
Cheng Wan
Lianmin Zheng
parent
56f06278c6
commit
2495c02c2c
@@ -230,7 +230,7 @@ def _spawn_server_process(
|
||||
kv_canary="raise",
|
||||
kv_canary_real_data="partial",
|
||||
kv_canary_sweep_interval=100,
|
||||
disable_piecewise_cuda_graph=True,
|
||||
disable_prefill_cuda_graph=True,
|
||||
)
|
||||
launch_kwargs.update(engine_kwargs)
|
||||
http_port = launch_kwargs["port"]
|
||||
|
||||
Reference in New Issue
Block a user