|
where reranking mattered
|
10-19-2026, 12:44 AM
I think the bottleneck is somewhere else. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
If you post your exact settings, people here can probably narrow it down pretty fast. |
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
where reranking mattered - by kernelghost - 10-16-2026, 10:34 AM
Re: where reranking mattered - by modrunner27 - 10-16-2026, 11:33 AM
Re: where reranking mattered - by homelabhenry - 10-17-2026, 12:05 AM
Re: where reranking mattered - by deltastation - 10-17-2026, 12:23 PM
Re: where reranking mattered - by phasenode - 10-19-2026, 03:31 AM
Re: where reranking mattered - by tinycontext - 10-18-2026, 07:45 PM
Re: where reranking mattered - by quietsupply11 - 10-19-2026, 12:44 AM
Re: where reranking mattered - by bytelab - 10-19-2026, 12:48 AM
Re: where reranking mattered - by turbogrid11 - 10-19-2026, 03:31 AM
Re: where reranking mattered - by homelabhenry - 10-19-2026, 04:56 AM
|
