mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2025-09-05 20:19:51 +00:00
112 lines
No EOL
3.7 KiB
YAML
112 lines
No EOL
3.7 KiB
YAML
- match:
|
|
name: "^model\\.layers\\.([012])\\."
|
|
class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding
|
|
replace:
|
|
class: ktransformers.operators.RoPE.RotaryEmbedding
|
|
kwargs:
|
|
generate_device: "cuda:0"
|
|
prefill_device: "cuda:0"
|
|
- match:
|
|
name: "^model\\.layers\\.([012])$" # regular expression
|
|
class: torch.nn.Linear # only match modules matching name and class simultaneously
|
|
replace:
|
|
class: ktransformers.operators.linear.KTransformersLinear # optimized Kernel on quantized data types
|
|
kwargs:
|
|
generate_device: "cuda:0"
|
|
prefill_device: "cuda:0"
|
|
generate_op: "KLinearMarlin"
|
|
prefill_op: "KLinearTorch"
|
|
- match:
|
|
name: "^model\\.layers\\.([012])\\.mlp$"
|
|
class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeSparseMoeBlock
|
|
replace:
|
|
class: ktransformers.operators.experts.KQwen2MoeSparseMoeBlock # mlp module with custom forward function
|
|
- match:
|
|
name: "^model\\.layers\\.([012])\\.mlp\\.experts$"
|
|
replace:
|
|
class: ktransformers.operators.experts.KTransformersExperts # custom MoE Kernel with expert paralleism
|
|
# device: "cpu" # which devices to load this module when initializing
|
|
kwargs:
|
|
prefill_device: "cuda:0"
|
|
prefill_op: "KExpertsTorch"
|
|
generate_device: "cpu"
|
|
generate_op: "KExpertsCPU"
|
|
out_device: "cuda:0"
|
|
recursive: False # don't recursively inject submodules of this module
|
|
|
|
- match:
|
|
name: "^model\\.layers\\.([12][0-9]|[3-9])\\."
|
|
class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding
|
|
replace:
|
|
class: ktransformers.operators.RoPE.RotaryEmbedding
|
|
kwargs:
|
|
generate_device: "cuda:1"
|
|
prefill_device: "cuda:1"
|
|
- match:
|
|
name: "^model\\.layers\\.([12][0-9]|[3-9])$" # 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\\.([12][0-9]|[3-9])\\.mlp$"
|
|
class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeSparseMoeBlock
|
|
replace:
|
|
class: ktransformers.operators.experts.KQwen2MoeSparseMoeBlock # mlp module with custom forward function
|
|
- match:
|
|
name: "^model\\.layers\\.([12][0-9]|[3-9])\\.mlp\\.experts$"
|
|
replace:
|
|
class: ktransformers.operators.experts.KTransformersExperts # custom MoE Kernel with expert paralleism
|
|
# device: "cpu" # which devices to load this module when initializing
|
|
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.embed_tokens"
|
|
replace:
|
|
class: "default"
|
|
kwargs:
|
|
generate_device: "cpu"
|
|
prefill_device: "cpu"
|
|
|
|
- match:
|
|
name: "(^model.norm)|(^lm_head)"
|
|
replace:
|
|
class: "default"
|
|
kwargs:
|
|
generate_device: "cuda:1"
|
|
prefill_device: "cuda:1"
|
|
|
|
- match:
|
|
name: "^model$"
|
|
replace:
|
|
class: "ktransformers.operators.layer_wise_prefill.KQwen2MoeModel"
|
|
kwargs:
|
|
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
|
|
transfer_map:
|
|
3: "cuda:1"
|
|
|
|
- match:
|
|
name: "^model\\.layers\\.([012])\\."
|
|
replace:
|
|
class: "default"
|
|
kwargs:
|
|
generate_device: "cuda:0"
|
|
prefill_device: "cuda:0"
|
|
|
|
- match:
|
|
name: "^model\\.layers\\.([12][0-9]|[3-9])\\."
|
|
replace:
|
|
class: "default"
|
|
kwargs:
|
|
generate_device: "cuda:1"
|
|
prefill_device: "cuda:1" |