CAD: Disaggregating Core Attention for Efficient Long-Context LLM Training
(hao-ai-lab.github.io)
6 pts| 2 months ago | discuss
ginda307's submissions
Disaggregated Inference: 18 Months Later
(hao-ai-lab.github.io)
1 pts| 4 months ago | discuss
Reasoning Without Hesitating: Efficient Cot Through Certainty Probing
(hao-ai-lab.github.io)
20 pts| 1 year ago | 5 comments
page 1