uodata

examples/inference/qwen3vl.yaml

+model_name_or_path: Qwen/Qwen3-VL-4B-Instruct
+template: qwen3_vl_nothink
+infer_backend: huggingface  # choices: [huggingface, vllm, sglang, ktransformers]
+trust_remote_code: true

examples/ktransformers/infer_lora/deepseek2_lora_sft_kt.yaml

+model_name_or_path: deepseek-ai/DeepSeek-V2-Lite
+adapter_name_or_path: saves/Kllama_deepseekV2
+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-V2-Lite-Chat-sft-amx.yaml
+cpu_infer: 32
+chunk_size: 8192

examples/ktransformers/infer_lora/deepseek3_kt.yaml

+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