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:
Lianmin Zheng
2025-05-12 00:17:33 -07:00
committed by GitHub
parent 7d3a3d4510
commit fba8eccd7e
27 changed files with 293 additions and 121 deletions

View File

@@ -330,7 +330,7 @@ class Engine(EngineBase):
return {
**dataclasses.asdict(self.tokenizer_manager.server_args),
**self.scheduler_info,
**internal_states,
"internal_states": internal_states,
"version": __version__,
}

View File

@@ -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__,
}