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, 10:45 UTC
[Misc] Fix CI lint (#9085)
Cody Yu committed
Oct 4, 2024 at 16:07 UTC
27302dd5841d4b0fa4788076ad9ff2993e133409
1 file changed
+3
-1
benchmarks/benchmark_prefix_caching.py
+3
-1
@@ -194,7 +194,9 @@ if __name__ == "__main__":
194
default='128:256',
195
help='Range of input lengths for sampling prompts,'
196
'specified as "min:max" (e.g., "128:256").')
197
- parser.add_argument("--seed", type=int, default=0,
197
+ parser.add_argument("--seed",
198
+ type=int,
199
+ default=0,
200
help='Random seed for reproducibility')
201
args = parser.parse_args()
202
main(args)