@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 5 lines 237 Bytes
Raw
1 model_name: "mistralai/Mixtral-8x7B-v0.1"
2 accuracy_threshold: 0.58
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --enable-expert-parallel --moe-backend=flashinfer_cutlass"