vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2026-05-01 21:21:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

[feature] add support for building docker image

Browse source
This commit is contained in:
chenxl 2024-08-01 04:01:00 +00:00
parent 112cb3c962
commit 86ba1336a9
4 changed files with 84 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

6
doc/en/deepseek-v2-injection.md
View file

@ -43,7 +43,11 @@ In the current version of KTransformers, we utilize Marlin for GPU kernels and l
<img alt="CPUInfer Performance" src="../assets/cpuinfer.png" width=80%>
</picture>
</p>
<p align="center">
<picture>
<img alt="marlin performance" src="https://github.com/IST-DASLab/marlin/blob/master/assets/sustained.png?raw=true" width=80%>
</picture>
</p>
### Arithmetic Intensity Guided Offloading