vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-09 22:05:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update v3 single gpu rule yaml;

Browse source
This commit is contained in:
Azure 2025-02-04 16:14:35 +00:00
parent 907251c743
commit ee24a27001
2 changed files with 12 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

15
ktransformers/optimize/optimize_rules/DeepSeek-V3-Chat.yaml
View file

@ -1,7 +1,7 @@
- match:
class: ktransformers.models.modeling_deepseek.DeepseekV3YarnRotaryEmbedding
class: ktransformers.models.modeling_deepseek_v3.DeepseekV3RotaryEmbedding
replace:
class: ktransformers.operators.RoPE.YarnRotaryEmbedding
class: ktransformers.operators.RoPE.RotaryEmbeddingV3
kwargs:
generate_device: "cuda"
prefill_device: "cuda"
@ -17,12 +17,19 @@
prefill_op: "KLinearTorch"
- match:
name: "^model\\.layers\\..*\\.mlp$"
class: ktransformers.models.modeling_deepseek.DeepseekV2MoE
class: ktransformers.models.modeling_deepseek_v3.DeepseekV3MoE
replace:
class: ktransformers.operators.experts.KDeepseekV2MoE # mlp module with custom forward function
class: ktransformers.operators.experts.KDeepseekV3MoE # mlp module with custom forward function
kwargs:
generate_device: "cuda"
prefill_device: "cuda"
- match:
class: ktransformers.models.modeling_deepseek_v3.MoEGate
replace:
class: ktransformers.operators.gate.KMoEGate
kwargs:
generate_device: "cuda:0"
prefill_device: "cuda:0"
- match:
name: "^model\\.layers\\..*\\.mlp\\.experts$"
replace: