TechnologyHacker News• 15h agoStochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing1 points, 0 comments on Hacker News
AI & MLHacker News• 19h agoModel routing is a fix for AI overspending, a problem for OpenAI and Anthropic3 points, 0 comments on Hacker News
TechnologyHacker News• 22h agoTrace-Based Adaptive Cost-Efficient Routing2 points, 1 comments on Hacker News