Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Login
Top
New
Best
Ask
Show
Jobs
RIS-Kernel: Running 64k context LLMs on CPU via sparse attention | Heykuki News
RIS-Kernel: Running 64k context LLMs on CPU via sparse attention
github.com/santosardr
2 points
santosardr
5 days ago
Add Comment
Loading...