xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-12 20:37:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add tpu

Browse Source
This commit is contained in:
Woosuk Kwon 2024-04-26 08:54:52 +00:00
parent 07be6ed3eb
commit 278e8a1adc
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
benchmarks/benchmark_throughput.py
View File

@ -335,7 +335,7 @@ if __name__ == "__main__":
"--device", "--device",
type=str, type=str,
default="cuda", default="cuda",
choices=["cuda", "cpu"], choices=["cuda", "cpu", "tpu"],
help='device type for vLLM execution, supporting CUDA and CPU.') help='device type for vLLM execution, supporting CUDA and CPU.')
parser.add_argument( parser.add_argument(
"--enable-prefix-caching", "--enable-prefix-caching",