vllm/tests/evals/gsm8k/configs/Qwen3.5-35B-A3B-FP8-DEP2.yaml

model_name: "Qwen/Qwen3.5-35B-A3B-FP8"
accuracy_threshold: 0.86
num_questions: 1319
num_fewshot: 5
server_args: >-
  --max-model-len 4096
  --data-parallel-size 2
  --enable-expert-parallel
  --kv-cache-dtype fp8