CUDA_VISIBLE_DEVICES=4,5,6,7 python tools/eval_aime2025_vllm.py \
  --model /mnt/disk1/yihao/Lightning-OPD/checkpoints/qwen3-4b-lightning-opd-hf \
  --num-gpus 4 \
  --prompt-template paper \
  --n-samples 32 \
  --temperature 0.6 \
  --top-p 0.95 \
  --max-tokens 32768 \
  --enable-thinking \
  --output outputs/aime2025_qwen3_4b_lightning_opd.jsonl


# CUDA_VISIBLE_DEVICES=0,2 python tools/eval_aime2025_vllm.py \
#     --model /mnt/disk1/yihao/Lightning-OPD/checkpoints/qwen3-4b-lightning-opd-hf \
#     --num-gpus 2 \
#     --n-samples 1 \
#     --temperature 0.0 \
#     --top-p 1.0 \
#     --max-tokens 32768 \
#     --prompt-template paper \
#     --hf-cache /mnt/disk1/yihao/hf_cache \
#     --output outputs/aime2024_qwen3_4b_poe_distill_lora_paper_n1_32k.jsonl \
#     --enable-thinking