N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
TurboPrefill: 2.7× faster than llama.cpp Pipeline Parallel on Llama-3-70B
(
github.com
)
3 points by
trykhlieb
1 days ago
|
0 comments
add comment
Rendered at 14:38:59 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
1 days ago
[-]