DeepSeek-V2-Chat.yaml

- match:
    class: ktransformers.models.modeling_deepseek.DeepseekV2YarnRotaryEmbedding
  replace:
    class: ktransformers.operators.RoPE.YarnRotaryEmbedding
    kwargs:
      generate_device: "cuda"
      prefill_device: "cuda"
- match:
    name: "^model\\.layers\\.(?!.*self_attn\\.kv_b_proj).*$"  # regular expression 
    class: torch.nn.Linear  # only match modules matching name and class simultaneously
  replace:
    class: ktransformers.operators.linear.KTransformersLinear  # optimized Kernel on quantized data types
    kwargs:
      generate_device: "cuda"
      prefill_device: "cuda"
      generate_op: "KLinearMarlin"
      prefill_op: "KLinearTorch"

- match:
    name: "^lm_head"
    class: torch.nn.Linear
  replace:
    class: ktransformers.operators.linear.KTransformersLinear
    kwargs:
      generate_device: "cuda"
      prefill_device: "cuda"
      generate_op: "KLinearMarlin"
      prefill_op: "KLinearTorch"

- match:
    name: "^model\\.layers\\..*\\.mlp$"
    class: ktransformers.models.modeling_deepseek.DeepseekV2MoE
  replace:
    class: ktransformers.operators.experts.KDeepseekV2MoE     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda"
      prefill_device: "cuda"
- match:
    name: "^model\\.layers\\..*\\.mlp\\.experts$"
  replace:
    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
    kwargs:
      prefill_device: "cuda"
      prefill_op: "KExpertsTorch"
      generate_device: "cpu"
      generate_op: "KExpertsCPU"
      out_device: "cuda"
  recursive: False # don't recursively inject submodules of this module
- match:
    name: "^model\\.layers\\..*\\.self_attn$"
  replace:
    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
    kwargs:
      generate_device: "cuda"
      prefill_device: "cuda"
- match:
    name: "^model$"
  replace:
    class: "ktransformers.operators.models.KDeepseekV2Model"
    kwargs:
      per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
- match:
    name: "^model.embed_tokens"
  replace:
    class: "default"
    kwargs:
      generate_device: "cpu"
      prefill_device: "cpu"