@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 5 lines 234 Bytes
Raw
1 model_name: "Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8"
2 accuracy_threshold: 0.88
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: "--enforce-eager --max-model-len 8192 --tensor-parallel-size 2 --linear-backend marlin --moe-backend marlin"