From 51d3cb951d5666b518a937f90477fe131d61c687 Mon Sep 17 00:00:00 2001 From: Woosuk Kwon Date: Thu, 30 Nov 2023 00:00:32 -0800 Subject: [PATCH] Remove max_num_seqs in latency benchmark script (#1855) --- benchmarks/benchmark_latency.py | 1 - 1 file changed, 1 deletion(-) diff --git a/benchmarks/benchmark_latency.py b/benchmarks/benchmark_latency.py index a0015ab1..8d9e177d 100644 --- a/benchmarks/benchmark_latency.py +++ b/benchmarks/benchmark_latency.py @@ -19,7 +19,6 @@ def main(args: argparse.Namespace): tokenizer=args.tokenizer, quantization=args.quantization, tensor_parallel_size=args.tensor_parallel_size, - max_num_seqs=args.batch_size, trust_remote_code=args.trust_remote_code, dtype=args.dtype, )