Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
RIS-Kernel: Running 64k context LLMs on CPU via sparse attention
(
github.com/santosardr
)
2 points
by
santosardr
11 hours ago
|
past
|
discuss
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
