Skip to content

GitLab

"vllm/model_executor/models/iquest_loopcoder.py" did not exist on "ca4eb82bcba97f4fb0a377287ff4d36e19c3d33e"
Unverified Commit 27208be6 authored by Woosuk Kwon's avatar Woosuk Kwon Committed by GitHub
Browse files

[Kernel] Add back batch size 1536 and 3072 to MoE tuning (#5242)

parent 87d5abef
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 1 deletion
benchmarks/kernels/benchmark_moe.py
View file @ 27208be6
...@@ -254,7 +254,9 @@ def main(args: argparse.Namespace): ...@@ -254,7 +254,9 @@ def main(args: argparse.Namespace):
use_fp8 = args.dtype == "fp8" use_fp8 = args.dtype == "fp8"
if args.batch_size is None: if args.batch_size is None:
batch_sizes = [1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096] batch_sizes = [
1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 1536, 2048, 3072, 4096
]
else: else:
batch_sizes = [args.batch_size] batch_sizes = [args.batch_size]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment