@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 10 lines 239 Bytes
Raw
1 model_name: "openai/gpt-oss-20b"
2 accuracy_threshold: 0.30
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: >-
6 --enforce-eager
7 --max-model-len 8192
8 --moe-backend humming
9 env:
10 VLLM_HUMMING_INPUT_QUANT_CONFIG: '{"dtype":"float8e4m3"}'