model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"
tasks:
- name: "gsm8k"
  metrics:
  - name: "exact_match,strict-match"
    value: 0.7142
  - name: "exact_match,flexible-extract"
    value: 0.4579
env_vars:
  VLLM_USE_FLASHINFER_MOE_FP8: "1"
  VLLM_FLASHINFER_MOE_BACKEND: "throughput"
limit: 1319
num_fewshot: 5
max_model_len: 262144
kv_cache_dtype: fp8
enforce_eager: false
apply_chat_template: true
fewshot_as_multiturn: true
trust_remote_code: true