10-18-2026, 06:36 PM
Good point. I ended up in about the same place using TensorRT-LLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
|
running local models on a phone for Phi
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
running local models on a phone for Phi - by fusedriver - 10-15-2026, 05:06 PM
Re: running local models on a phone for Phi - by routeline23 - 10-16-2026, 05:38 PM
Re: running local models on a phone for Phi - by cudacrate - 10-16-2026, 09:49 PM
Re: running local models on a phone for Phi - by amberrunner - 10-18-2026, 08:17 PM
Re: running local models on a phone for Phi - by relaysupply90 - 10-18-2026, 10:00 AM
Re: running local models on a phone for Phi - by sparrowworks88 - 10-18-2026, 06:26 PM
Re: running local models on a phone for Phi - by rocmmixer - 10-18-2026, 06:36 PM
Re: running local models on a phone for Phi - by plainline - 10-18-2026, 08:41 PM
Re: running local models on a phone for Phi - by batchpeak - 10-18-2026, 09:12 PM
Re: running local models on a phone for Phi - by llmpeak - 10-18-2026, 10:00 PM
Re: running local models on a phone for Phi - by sparrowworks88 - 10-19-2026, 04:39 AM
|
Users browsing this thread: 1 Guest(s)