@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 5 lines 171 Bytes
Raw
1 model_name: "amd/Qwen1.5-MoE-A2.7B-Chat-w-int8-a-int8-sym"
2 accuracy_threshold: 0.50
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: "--enforce-eager --max-model-len 4096"