mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-10-24 10:46:18 +08:00
bb8a2bf1de7337bf12cbc4003200bd0976afc8d4
Description
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
112 MiB
Languages
Python
56.8%
C++
35.2%
Cuda
4.2%
Shell
1.2%
CMake
0.8%
Other
1.5%