Blealtan

efficient-kan. An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

RWKV-LM-LoRA. RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Moonet. A semi-static typed superset of the programming language, Lua. Implemented in dotnet and use dotnet as its runtime.

RWKV-CUDA. The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

ohos-openconnect-lib. C

tvm. Open deep learning compiler stack for cpu, gpu and specialized accelerators

2015-Web-Design-Lecture. The web designing lecture presentation for members of SCGYSU of USTC.