>1B tokens/minute/GPU by combining query planner and inference engine
15d
5
2
- Published
- Collected
Read the full article at news.ycombinator.com
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Hacker News (AI).
15d
5
2
overfeed.news indexes and links. We publish a short excerpt — the full article stays at Hacker News (AI).
