RWKV
RWKV (pronounced as RwaKuv) is an RNN with GPT-level LLM performance, which can also be directly trained like a GPT transformer (parallelizable).
So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free.
Projects
RWKV-Runner
RWKV GUI with one-click install and API
RWKV.cpp
Fast CPU/cuBLAS/CLBlast inference: int4/int8/fp16/fp32
RWKV-server
Fastest GPU inference API with vulkan (good for nvidia/amd/intel)
RWKV-accelerated
Fast GPU inference with cuda/amd/vulkan
RWKV-LM
Training RWKV
RWKV-LM-LoRA
LoRA finetuning
ChatRWKV
Chat with RWKV (in console)
Misc
RWKV wiki
Community wiki (with guide and FAQ)
RWKV pip package
Official RWKV pip package
RWKV models
Latest RWKV models on Hugging Face
中文介绍
中文介绍，对话和小说 Demo