A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 23:15 UTC
[Misc] Remove #4789 workaround left in vllm/entrypoints/openai/run_batch.py (#5756)
zifeitong committed
Jun 21, 2024 at 20:33 UTC
ff9ddbceee63efba6ba1f8d4dc66a92f1191da04
1 file changed
-4
vllm/entrypoints/openai/run_batch.py
-4
@@ -1,5 +1,4 @@
1
import asyncio
2
-import sys
2
from io import StringIO
3
from typing import Awaitable, List
4
@@ -137,9 +136,6 @@ async def main(args):
136
output_buffer.seek(0)
137
await write_file(args.output_file, output_buffer.read().strip())
138
140
- # Temporary workaround for https://github.com/vllm-project/vllm/issues/4789
141
- sys.exit(0)
142
-
139
140
if __name__ == "__main__":
141
args = parse_args()