top | item 47142293

(no title)

smcleod | 5 days ago

Managed to get 6.4tk/s with some modifications: https://github.com/PureBee/purebee/pull/1

discuss

order

benryanx|3 days ago

That's the postMessage bottleneck - PR #1 replaces it with Atomics-based dispatch which should push utilisation much higher. Early numbers look like 6.4 tok/sec on M2 Max