cd Quark/examples/torch/language_modeling/llm_ptq/
exclude_layers="*self_attn* *mlp.gate *lm_head *mm_projector* *vision_tower*"

python quantize_quark.py \
    --model_dir moonshotai/Kimi-K2.5 \
    --quant_scheme mxfp4 \
    --exclude_layers  $exclude_layers \
    --output_dir amd/Kimi-K2.5-MXFP4 \
    --file2file_quantization

pip install lm-eval
pip install lm-eval[api]

export VLLM_ROCM_USE_AITER=1

vllm serve amd/Kimi-K2.5-MXFP4 -tp 4 \
  --mm-encoder-tp-mode data \
  --tool-call-parser kimi_k2 \
  --reasoning-parser kimi_k2 \
  --enforce-eager \
  --trust-remote-code

lm_eval \
  --model local-completions \
  --model_args "model=amd/Kimi-K2.5-MXFP4,base_url=http://0.0.0.0:8000/v1/completions,tokenized_requests=False,tokenizer_backend=None,num_concurrent=32" \
  --tasks gsm8k \
  --num_fewshot 5 \
  --batch_size 1