dual GPU split inference for Mistral

Thread Rating:

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

Linear Mode

dual GPU split inference for Mistral

batchwire Offline

Offline

Member

Posts: 68
Threads: 9
Joined: Sep 2026
Reputation: 0

#4

09-01-2026, 09:51 PM

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

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

dual GPU split inference for Mistral - by paperrunner - 08-29-2026, 08:21 AM

Re: dual GPU split inference for Mistral - by turbogrid11 - 08-31-2026, 08:34 AM

Re: dual GPU split inference for Mistral - by cudapoint - 08-31-2026, 09:22 AM

Re: dual GPU split inference for Mistral - by batchwire - 09-01-2026, 09:51 PM

Re: dual GPU split inference for Mistral - by turboyard94 - 09-02-2026, 10:27 PM

Re: dual GPU split inference for Mistral - by dockkite69 - 09-07-2026, 07:00 PM

Re: dual GPU split inference for Mistral - by dockkite69 - 09-04-2026, 10:55 AM

Re: dual GPU split inference for Mistral - by rocmriley - 09-04-2026, 12:13 PM

Re: dual GPU split inference for Mistral - by batchwire - 09-04-2026, 01:14 PM

Re: dual GPU split inference for Mistral - by signaltrack44 - 09-07-2026, 01:45 PM

Re: dual GPU split inference for Mistral - by vrambandit - 09-08-2026, 07:16 PM

Re: dual GPU split inference for Mistral - by amberhall - 09-07-2026, 02:37 PM

Re: dual GPU split inference for Mistral - by circuitwire58 - 09-07-2026, 02:47 PM

Re: dual GPU split inference for Mistral - by rocmriley - 09-08-2026, 09:33 PM

Re: dual GPU split inference for Mistral - by paperrunner - 09-09-2026, 01:59 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)