Log if cuda graph is used & extend cuda graph capture to cuda-graph-max-bs (#6201)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
This commit is contained in:
co-authored by
SangBin Cho
parent
7d3a3d4510
commit
fba8eccd7e
@@ -222,7 +222,7 @@ async def get_server_info():
|
||||
return {
|
||||
**dataclasses.asdict(_global_state.tokenizer_manager.server_args),
|
||||
**_global_state.scheduler_info,
|
||||
**internal_states,
|
||||
"internal_states": internal_states,
|
||||
"version": __version__,
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user