@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 5 lines 157 Bytes
Raw
1 model_name: "Qwen/Qwen3-4B"
2 accuracy_threshold: 0.80
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: "--kv-cache-dtype turboquant_k8v4 --max-model-len 4096"