[Auto Sync] Update http_server.py, io_struct.py, scheduler_... (20251120) (#13679)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Zhuqi Li <zhli@x.ai>
This commit is contained in:
Lianmin Zheng
2025-11-20 23:17:15 -08:00
committed by GitHub
co-authored by github-actions[bot] <github-actions[bot]@users.noreply.github.com> Zhuqi Li
parent 4360279036
commit 90a0133515
6 changed files with 35 additions and 0 deletions
+5
View File
@@ -37,6 +37,7 @@ class BenchArgs:
profile: bool = False
profile_steps: int = 3
profile_by_stage: bool = False
profile_name_prefix: str = ""
@staticmethod
def add_cli_args(parser: argparse.ArgumentParser):
@@ -44,6 +45,9 @@ class BenchArgs:
parser.add_argument("--port", type=int, default=BenchArgs.port)
parser.add_argument("--batch-size", type=int, default=BenchArgs.batch_size)
parser.add_argument("--temperature", type=float, default=BenchArgs.temperature)
parser.add_argument(
"--profile-name-prefix", type=str, default=BenchArgs.profile_name_prefix
)
parser.add_argument(
"--max-new-tokens", type=int, default=BenchArgs.max_new_tokens
)
@@ -133,6 +137,7 @@ def send_one_prompt(args):
None,
None,
args.profile_by_stage,
args.profile_name_prefix,
)
response = requests.post(