The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
Paper • 2609.18063 • Published • 27
🔄 In a Training Loop
Andy Chen
andynoodles
P(doom) 100%
AI & ML interests
Feel free to contact me through Linkedin
Recent Activity
liked a model about 1 hour ago
LiquidAI/LFM2.5-24B-A2B liked a model 6 days ago
Cloudflare/clef-flash liked a model 6 days ago
ornith-ai/Ornith-1.5-35B-A3B-FP8Organizations
upvoted 2
papers 26 days ago