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

[feature] release 0.1.3

Browse source
This commit is contained in:
chenxl 2024-08-28 16:11:43 +00:00
parent 67f8b370c3
commit 4d1d561d28
58 changed files with 11709 additions and 374 deletions
Download patch file Download diff file Expand all files Collapse all files

9
ktransformers/optimize/optimize_rules/Qwen2-57B-A14B-Instruct.yaml
View file

@ -1,3 +1,10 @@
- match:
name: "^model\\.layers\\..*\\."
replace:
class: "default"
kwargs:
generate_device: "cuda"
prefill_device: "cuda"
- match:
class: ktransformers.models.modeling_qwen2_moe.Qwen2MoeRotaryEmbedding
replace:
@ -54,4 +61,4 @@
class: "default"
kwargs:
generate_device: "cuda"
prefill_device: "cuda"
prefill_device: "cuda"