AnalysisDevelopers
14 days ago
Flash attention 3/4 via kernels library recommended

Hugging Face
@huggingfaceThe AI community building the future. https://t.co/TpiXQMQ9rZ
NYC and Paris and ๐huggingface.co

Hugging Face
@huggingface
RT @RisingSayak: I am bullish and biased, but the best way way use flash attention 3 or 4 is via ๐ค kernels: ``` from kernels import get_keโฆ
ยท
14 days ago