mirror of https://github.com/wassname/vllm.git synced 2026-07-07 05:20:48 +08:00

Files

T

Kunshang Ji 96b6f475dd Remove hardcoded device="cuda" to support more devices (#2503 )

Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>

2024-02-01 15:46:39 -08:00

2024-02-01 15:46:39 -08:00

benchmark_latency.py

2024-02-01 15:46:39 -08:00

benchmark_serving.py

2024-01-23 15:53:06 -08:00

benchmark_throughput.py

2024-02-01 15:46:39 -08:00

launch_tgi_server.sh

2023-06-26 13:15:35 -07:00

README.md

2023-06-17 03:07:40 -07:00

Benchmarking vLLM

Downloading the ShareGPT dataset

You can download the dataset by running:

wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json