model_name_or_path: opensourcerelease/DeepSeek-V3-bf16
template: deepseek
infer_backend: ktransformers  # choices: [huggingface, vllm, sglang, ktransformers]
trust_remote_code: true

use_kt: true # use KTransformers as LoRA sft backend to inference
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V3-Chat-sft-amx-multi-gpu.yaml
cpu_infer: 32
chunk_size: 8192