best local runtime for mixed models for Gemma

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

best local runtime for mixed models for Gemma

vectorember Offline

Offline

Junior Member

Posts: 23
Threads: 8
Joined: Sep 2026
Reputation: 0

#10

10-12-2026, 07:17 PM

Quote:Interesting, I hadn't tried that. That matches what I saw on GB200.

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.

trying not to rebuild again

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

best local runtime for mixed models for Gemma - by fusedhall - 10-11-2026, 04:19 AM

Re: best local runtime for mixed models for Gemma - by amberhall - 10-11-2026, 05:15 AM

Re: best local runtime for mixed models for Gemma - by vectorhouse71 - 10-11-2026, 05:28 AM

Re: best local runtime for mixed models for Gemma - by latentscope35 - 10-11-2026, 02:05 PM

Re: best local runtime for mixed models for Gemma - by fusedhall - 10-11-2026, 03:37 PM

Re: best local runtime for mixed models for Gemma - by mellowwire98 - 10-11-2026, 11:59 PM

Re: best local runtime for mixed models for Gemma - by quantshed - 10-12-2026, 06:55 AM

Re: best local runtime for mixed models for Gemma - by amberhall - 10-12-2026, 04:01 AM

Re: best local runtime for mixed models for Gemma - by vectorember - 10-12-2026, 06:22 AM

Re: best local runtime for mixed models for Gemma - by vectorember - 10-12-2026, 07:17 PM

Re: best local runtime for mixed models for Gemma - by llm_wren - 10-12-2026, 08:08 PM

Re: best local runtime for mixed models for Gemma - by vectorcrate98 - 10-12-2026, 09:09 PM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)