← Back to context Comment by smusamashah 5 days ago Does it mean if it was embedded on a Talaas chip, it could generate ~50,000+ tokens per second? 1 comment smusamashah Reply Havoc 4 days ago Think pretty much anything is going to get a enormous speed boost if the model isn’t undergoing mem latency but is just inherently baked into the circuits asic style
Havoc 4 days ago Think pretty much anything is going to get a enormous speed boost if the model isn’t undergoing mem latency but is just inherently baked into the circuits asic style
Think pretty much anything is going to get a enormous speed boost if the model isn’t undergoing mem latency but is just inherently baked into the circuits asic style