|
flux pipeline local tips for Gemma
|
08-26-2026, 12:31 AM
Quote:That matches what I was seeing. I ended up in about the same place using MLX. The biggest change for me was simplifying the stack instead of adding on Ran a quick check on my box. On dual 3090 with TensorRT-LLM, I saw basically the same behavior.
post logs or it didn't happen
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
flux pipeline local tips for Gemma - by bytelab - 08-23-2026, 10:09 PM
Re: flux pipeline local tips for Gemma - by phaseshed - 08-23-2026, 10:21 PM
Re: flux pipeline local tips for Gemma - by signaltrack44 - 08-25-2026, 10:23 AM
Re: flux pipeline local tips for Gemma - by vramforge - 08-25-2026, 10:47 AM
Re: flux pipeline local tips for Gemma - by cudacrate - 08-25-2026, 11:18 AM
Re: flux pipeline local tips for Gemma - by vectorhouse71 - 08-25-2026, 12:19 PM
Re: flux pipeline local tips for Gemma - by benchplease - 08-26-2026, 12:31 AM
Re: flux pipeline local tips for Gemma - by turboscope5 - 08-27-2026, 12:50 PM
|
