Commit History

streaming via transformers
225e073

lsb commited on

try to keep a larger model in /dev/shm
7672916

lsb commited on

try a smaller model with mlock and flash attention
3fb9f48

lsb commited on

streaming
b0f4561

lsb commited on

maybe verbosity will tell me cuda or no
42cc4f3

lsb commited on

use llama cpp
c76cb37

lsb commited on

Duplicate from gradio-templates/chatbot
c7321cf
verified

lsb pngwn HF Staff commited on