RWKV is an 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.
Apache License 2.0
12.32k
stars
838
forks
source link
RWKV only show lower GPU memory occupancy when inference? #250
I tried to use RWKV(e.g., Vision-RWKV) in CV tasks. But I found RWKV shows similar GPU memory occupancy to full-attention Transformer (like ViT) when training. I found both RWKV and Vision-RWKV only present their inference memory occupancy in the paper.
The high memory consume is not friendly for my tasks. Do you have any advice?
I tried to use RWKV(e.g., Vision-RWKV) in CV tasks. But I found RWKV shows similar GPU memory occupancy to full-attention Transformer (like ViT) when training. I found both RWKV and Vision-RWKV only present their inference memory occupancy in the paper.
The high memory consume is not friendly for my tasks. Do you have any advice?