N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
A complete Llama2 inference engine that fits in 1356 bytes of x86 assembly
(
github.com
)
26 points by
monax
21 hours ago
|
0 comments
add comment
Rendered at 03:33:46 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.