Skip to content

AirLLM 2.8T LLM inference with single 4GB GPU

Commits on main

add request form
Yu Li committed 2 years ago
827f714
add request form
Yu Li committed 2 years ago
c2a1439
support baichuan mistral internlm
Yu Li committed 2 years ago
cabf98f
add some Chinese in readme
Yu Li committed 2 years ago
8287a46
clean up unnecessary logs
Yu Li committed 2 years ago
58e3873
support qwen
Yu Li committed 2 years ago
916efd5
add support of chatglm
Yu Li committed 2 years ago
64f3c1c
fix dependencies, improve readme
Yu Li committed 2 years ago
e5b1fcc
update readme
Yu Li committed 2 years ago
ecfe285
add logo
Yu Li committed 2 years ago
82201f9
support safetensors model
Yu Li committed 2 years ago
9e6557a
update readme
Yu Li committed 2 years ago
b099922
update readme
Yu Li committed 2 years ago
16e0942
update readme
Yu Li committed 2 years ago
2bacae2
update readme
Yu Li committed 2 years ago
953490e
update readme
Yu Li committed 2 years ago
bb62d8d
update readme
Yu Li committed 2 years ago
a524fc4
refine img
Yu Li committed 2 years ago
3ea32de
publish 2.0.0
Yu Li committed 2 years ago
19283f5
make sure its on cuda
Yu Li committed 2 years ago
d3511af
make sure its on cuda
Yu Li committed 2 years ago
9a5d4dc
make sure its on cuda
Yu Li committed 2 years ago
d1cec72
make sure its on cuda
Yu Li committed 2 years ago
290cfa1
make sure its on cuda
Yu Li committed 2 years ago
750a690
5c9fcfe
2048 block size for 8bit
Yu Li committed 2 years ago
5e5b362
2048 block size for 8bit
Yu Li committed 2 years ago
4679a5f
2048 block size for 8bit
Yu Li committed 2 years ago
f3d9067
loop 10 times in ut
Yu Li committed 2 years ago
6ad5ae8