xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 02:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Raise error for data-parallel with benchmark_throughput (#16737)

Browse Source 
Signed-off-by: Kartik Ramesh <kartikx2000@gmail.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
Kartik Ramesh 2025-04-21 10:51:43 -05:00 committed by GitHub
parent 55d6d3fdb8
commit 3b34fd5273
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
benchmarks/benchmark_throughput.py
View File

@ -523,6 +523,13 @@ def validate_args(args):
raise ValueError( raise ValueError(
"Tokenizer must be the same as the model for MII backend.") "Tokenizer must be the same as the model for MII backend.")
# --data-parallel is not supported currently.
# https://github.com/vllm-project/vllm/issues/16222
if args.data_parallel_size > 1:
raise ValueError(
"Data parallel is not supported in offline benchmark, \
please use benchmark serving instead")
if __name__ == "__main__": if __name__ == "__main__":
parser = FlexibleArgumentParser(description="Benchmark the throughput.") parser = FlexibleArgumentParser(description="Benchmark the throughput.")