HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Show HN: VLMs Can Respond Twice as Fast Without Losing Quality
github.com/sergey-automation
1 comment
a day ago
trykhlieb
2 points
2.
▲
Show HN: TurboPrefill – Multi-GPU prefill acceleration for llama.cpp
github.com/sergey-automation
discuss
18 days ago
trykhlieb
2 points