vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-14 00:59:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix readme; adjust param

Browse source
This commit is contained in:
TangJingqi 2024-08-29 10:40:08 +08:00
parent 233bbb8c55
commit abd4214b56
3 changed files with 5 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -46,7 +46,7 @@
replace:
class: "ktransformers.operators.models.KDeepseekV2Model"
kwargs:
per_layer_prefill_intput_threshold: 2000 # 0 is close layer wise prefill
per_layer_prefill_intput_threshold: 0 # 0 is close layer wise prefill
- match:
name: "^model.embed_tokens"
replace: