DeepSeek-V3-Chat-multi-gpu.yaml

- match:
    name: "^model.embed_tokens"
  replace:
    class: "default"
    kwargs:
        generate_device: "cpu"
        prefill_device: "cpu"

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\."
    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3RotaryEmbedding
  replace:
    class: ktransformers.operators.RoPE.YarnRotaryEmbeddingV3
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([3456][0-9])\\."
    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3RotaryEmbedding
  replace:
    class: ktransformers.operators.RoPE.YarnRotaryEmbeddingV3
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.(?!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:0"
      prefill_device: "cuda:0"
      generate_op: "KLinearMarlin"
      prefill_op: "KLinearTorch"

- match:
    name: "^model\\.layers\\.([3456][0-9])\\.(?!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:1"
      prefill_device: "cuda:1"
      generate_op: "KLinearMarlin"
      prefill_op: "KLinearTorch"
  
- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp$"
    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3MoE
  replace:
    class: ktransformers.operators.experts.KDeepseekV3MoE     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([3456][0-9])\\.mlp$"
    class: ktransformers.models.modeling_deepseek_v3.DeepseekV3MoE
  replace:
    class: ktransformers.operators.experts.KDeepseekV3MoE     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.gate$"
    class: ktransformers.models.modeling_deepseek_v3.MoEGate
  replace:
    class: ktransformers.operators.gate.KMoEGate
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([3456][0-9])\\.mlp\\.gate$"
    class: ktransformers.models.modeling_deepseek_v3.MoEGate
  replace:
    class: ktransformers.operators.gate.KMoEGate     # mlp module with custom forward function
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.mlp\\.experts$"
  replace:
    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
    kwargs:
      prefill_device: "cuda:0"
      prefill_op: "KExpertsTorch"
      generate_device: "cpu"
      generate_op:  "KExpertsCPU"
      out_device: "cuda:0"
  recursive: False # don't recursively inject submodules of this module

- match:
    name: "^model\\.layers\\.([3456][0-9])\\.mlp\\.experts$"
  replace:
    class: ktransformers.operators.experts.KTransformersExperts     # custom MoE Kernel with expert paralleism
    kwargs:
      prefill_device: "cuda:1"
      prefill_op: "KExpertsTorch"
      generate_device: "cpu"
      generate_op:  "KExpertsCPU"
      out_device: "cuda:1"
  recursive: False # don't recursively inject submodules of this module

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\.self_attn$"
  replace:
    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"
- match:
    name: "^model\\.layers\\.([3456][0-9])\\.self_attn$"
  replace:
    class: ktransformers.operators.attention.KDeepseekV2Attention # optimized MLA implementation
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"
- match:
    name: "^model$"
  replace:
    class: "ktransformers.operators.models.KDeepseekV2Model"
    kwargs:
      per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
      transfer_map: 
        30: "cuda:1"

- match:
    name: "^model\\.layers\\.(0|[1-9]|[12][0-9])\\."
  replace:
    class: "default"
    kwargs:
      generate_device: "cuda:0"
      prefill_device: "cuda:0"

- match:
    name: "^lm_head"
    class: torch.nn.Linear
  replace:
    class: ktransformers.operators.linear.KTransformersLinear
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"
      generate_op: "KLinearMarlin"
      prefill_op: "KLinearTorch"

- match:
    name: "(^model\\.layers\\.([3456][0-9])\\.)|(model.norm)"
  replace:
    class: "default"
    kwargs:
      generate_device: "cuda:1"
      prefill_device: "cuda:1"