@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 9 lines 225 Bytes
Raw
1 model_name: "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
2 accuracy_threshold: 0.85
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: >-
6 --max-model-len 4096
7 --tensor-parallel-size 2
8 --enable-expert-parallel
9 --async-scheduling