mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2025-09-08 21:49:39 +00:00
80 lines
2.7 KiB
YAML
80 lines
2.7 KiB
YAML
- match:
|
|
name: "rotary_emb$"
|
|
replace:
|
|
class: ktransformers.operators.RoPE.KQwen3MoeRotaryEmbedding
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|
|
- match:
|
|
name: "^lm_head$" # 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: "xpu"
|
|
prefill_device: "xpu"
|
|
generate_op: "KLinearIPEXLLM"
|
|
prefill_op: "KLinearIPEXLLM"
|
|
- match:
|
|
name: "^model\\.layers\\.(?!.*mlp\\.gate).*$" # regular expression
|
|
class: torch.nn.Linear # only match modules matching name and class simultaneously
|
|
replace:
|
|
class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|
|
generate_op: "KLinearIPEXLLM"
|
|
prefill_op: "KLinearIPEXLLM"
|
|
- match:
|
|
name: "^model\\.layers\\..*\\.mlp$"
|
|
class: transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeSparseMoeBlock
|
|
replace:
|
|
class: ktransformers.operators.experts.KQwen3MoeSparseMoeBlockV2 # mlp module with custom forward function
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|
|
- match:
|
|
name: "^model\\.layers\\..*\\.mlp\\.experts$"
|
|
replace:
|
|
class: ktransformers.operators.experts.KTransformersExpertsV2 # custom MoE Kernel with expert paralleism
|
|
kwargs:
|
|
prefill_device: "xpu"
|
|
prefill_op: "KExpertsTorch"
|
|
generate_device: "cpu"
|
|
generate_op: "KExpertsCPU"
|
|
out_device: "xpu"
|
|
recursive: False # don't recursively inject submodules of this module
|
|
- match:
|
|
name: "^model\\.layers\\..*\\.self_attn$"
|
|
replace:
|
|
class: ktransformers.operators.attention.KQwen3MoeAttentionIPEXLLM
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|
|
- match:
|
|
name: "^model$"
|
|
replace:
|
|
class: "ktransformers.operators.models.KQwen2MoeModel"
|
|
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"
|
|
- match:
|
|
class: transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeRMSNorm
|
|
replace:
|
|
class: ktransformers.operators.layernorm.KDeepseekRMSNormIPEXLLM
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|
|
- match:
|
|
class: transformers.models.qwen3_moe.modeling_qwen3_moe.Qwen3MoeMLP
|
|
replace:
|
|
class: ktransformers.operators.mlp.KQwen2MoeMLP
|
|
kwargs:
|
|
generate_device: "xpu"
|
|
prefill_device: "xpu"
|