squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Benchmark] Add cpu options to bench scripts (#3915)

Browse Source
This commit is contained in:
Zedong Peng 2024-04-10 12:30:03 +08:00 committed by GitHub
parent 11dd6ebb89
commit c013d32c75
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/benchmark_latency.py
View File

@ -169,8 +169,8 @@ if __name__ == '__main__':
"--device", "--device",
type=str, type=str,
default="cuda", default="cuda",
choices=["cuda"], choices=["cuda", "cpu"],
help='device type for vLLM execution, supporting CUDA only currently.') help='device type for vLLM execution, supporting CUDA and CPU.')
parser.add_argument('--block-size', parser.add_argument('--block-size',
type=int, type=int,
default=16, default=16,

4
benchmarks/benchmark_throughput.py
View File

@ -329,8 +329,8 @@ if __name__ == "__main__":
"--device", "--device",
type=str, type=str,
default="cuda", default="cuda",
choices=["cuda"], choices=["cuda", "cpu"],
help='device type for vLLM execution, supporting CUDA only currently.') help='device type for vLLM execution, supporting CUDA and CPU.')
parser.add_argument( parser.add_argument(
"--enable-prefix-caching", "--enable-prefix-caching",
action='store_true', action='store_true',