vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-04-28 11:49:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

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
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: