10-05-2026, 12:30 PM
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Worth testing the simpler explanation before adopting the more interesting one.
|
benchmark result I don't trust for FLUX
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
benchmark result I don't trust for FLUX - by quiethouse - 10-02-2026, 11:36 PM
Re: benchmark result I don't trust for FLUX - by batchsize - 10-03-2026, 11:51 PM
Re: benchmark result I don't trust for FLUX - by benchplease - 10-04-2026, 12:12 AM
Re: benchmark result I don't trust for FLUX - by cacheline - 10-04-2026, 12:27 AM
Re: benchmark result I don't trust for FLUX - by kernelghost - 10-04-2026, 12:55 AM
Re: benchmark result I don't trust for FLUX - by batchpeak - 10-05-2026, 01:01 AM
Re: benchmark result I don't trust for FLUX - by cacheline - 10-05-2026, 03:43 AM
Re: benchmark result I don't trust for FLUX - by oxiderunner - 10-05-2026, 12:30 PM
Re: benchmark result I don't trust for FLUX - by cacheline - 10-05-2026, 12:46 PM
Re: benchmark result I don't trust for FLUX - by quiethouse - 10-07-2026, 01:01 AM
|
Users browsing this thread: 1 Guest(s)