AlpinDale 9a7d5514c4 feat: introduce MQAphroditeEngine (#1056) 1 week ago
..
cutlass_benchmarks f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago
engine 9a7d5514c4 feat: introduce MQAphroditeEngine (#1056) 1 week ago
kernels 93bc863591 feat: Machete Kernels for Hopper GPUs (#842) 1 month ago
overheads f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago
README.md f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago
attention.py f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago
backend_request_func.py 563e8f7ac8 fix: latency and serving benchmarks (#841) 1 month ago
launch_tgi.sh 4d04ade9ef feat: fine-grained seeds (#279) 10 months ago
sonnet.txt f1d0b77c92 [0.6.0] Release Candidate (#481) 4 months ago

README.md

Benchmarking Aphrodite

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