vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-05 12:09:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

fix name

Browse source
This commit is contained in:
TangJingqi 2024-08-15 11:25:12 +08:00
parent 67043b4b5c
commit c47205dce9
6 changed files with 6 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat-multi-gpu-4.yaml
View file

@ -190,7 +190,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KDeepseekV2Model"
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
transfer_map:

2
ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat-multi-gpu.yaml
View file

@ -103,7 +103,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KDeepseekV2Model"
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
transfer_map:

2
ktransformers/optimize/optimize_rules/DeepSeek-V2-Chat.yaml
View file

@ -55,7 +55,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KDeepseekV2Model"
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
generate_device: "cuda"
prefill_device: "cuda"

2
ktransformers/optimize/optimize_rules/DeepSeek-V2-Lite-Chat-multi-gpu.yaml
View file

@ -103,7 +103,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KDeepseekV2Model"
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
transfer_map:

2
ktransformers/optimize/optimize_rules/Qwen2-57B-A14B-Instruct-multi-gpu.yaml
View file

@ -89,7 +89,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KQwen2MoeModel"
class: "ktransformers.operators.models.KQwen2MoeModel"
kwargs:
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
transfer_map:

2
ktransformers/optimize/optimize_rules/Qwen2-57B-A14B-Instruct.yaml
View file

@ -38,7 +38,7 @@
- match:
name: "^model$"
replace:
class: "ktransformers.operators.layer_wise_prefill.KQwen2MoeModel"
class: "ktransformers.operators.models.KQwen2MoeModel"
kwargs:
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
- match: