Qwen3-0.6B-MXFP8-humming.yaml · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

yaml 7 lines 163 Bytes

Raw

1	model_name: "mgoin/Qwen3-0.6B-MXFP8"
2	accuracy_threshold: 0.39
3	num_questions: 1319
4	num_fewshot: 5
5	server_args: >-
6	--max-model-len 8192
7	--linear-backend humming