09-15-2026, 11:42 AM
Good point. I ended up in about the same place using SGLang. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
|
embedding drift issues for Llama
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
embedding drift issues for Llama - by cachelab - 09-13-2026, 06:57 PM
Re: embedding drift issues for Llama - by macropoint - 09-15-2026, 06:57 AM
Re: embedding drift issues for Llama - by phaseport36 - 09-15-2026, 11:28 AM
Re: embedding drift issues for Llama - by vramarch - 09-15-2026, 11:42 AM
Re: embedding drift issues for Llama - by dockbrook21 - 09-16-2026, 12:01 PM
Re: embedding drift issues for Llama - by deepseeked - 09-16-2026, 05:45 PM
Re: embedding drift issues for Llama - by kernelmike - 09-16-2026, 04:35 PM
Re: embedding drift issues for Llama - by signaltrack44 - 09-16-2026, 10:03 PM
|
Users browsing this thread: 1 Guest(s)