| ▲ | Why Is Speculative Decoding Fast?(jbarrow.ai) | |||||||
| 37 points by gmays a day ago | 4 comments | ||||||||
| ▲ | ape4 6 minutes ago | parent | next [-] | |||||||
systemd-resolved can send your query to multiple servers and use the one that returns first. | ||||||||
| ▲ | ArashEdalat 20 minutes ago | parent | prev | next [-] | |||||||
we have action chunking in robotics for the same reason so VLAs can analyze faster and come to actions, the latency and inference are both slow so many steps need to come together for this to happen correctly | ||||||||
| ▲ | ArashEdalat 19 minutes ago | parent | prev [-] | |||||||
has anyone tried different approaches to this? | ||||||||
| ||||||||