# TODO(rob): enable
# model_name: "amd/Mixtral-8x7B-Instruct-v0.1-FP8-KV"
# accuracy_threshold: 0.62
# num_questions: 1319
# num_fewshot: 5
# server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --moe-backend=flashinfer_cutlass"