ifoxhz
- Karma
- 0
- Created
- ()
- Submissions
- 0
-
If we compress LLMs into neuromorphic chips to reduce inference latency, would it be relatively easy to achieve low-cost autonomous driving?
- Show HN: A local RAG desktop app: piFlow (github.com)
If we compress LLMs into neuromorphic chips to reduce inference latency, would it be relatively easy to achieve low-cost autonomous driving?