@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 7 lines 163 Bytes
Raw
1 model_name: "Qwen/Qwen3.5-4B"
2 needles: [2, 4, 8]
3 match_ratio_threshold:
4 2: 0.99
5 4: 0.84
6 8: 0.76
7 server_args: "--max-model-len 128K --reasoning-parser qwen3"