working config for 32k context

Thread Rating:

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

Linear Mode

working config for 32k context

audioriver Offline

Offline

Member

Posts: 69
Threads: 3
Joined: Sep 2026
Reputation: 0

#14

10-18-2026, 12:41 PM

I tested this tonight. On GB200 with PyTorch, I saw basically the same behavior. I expected the model choice to matter more than it did.

still benchmarking everything

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

working config for 32k context - by relayforge - 10-10-2026, 06:14 AM

Re: working config for 32k context - by batchshed - 10-10-2026, 08:39 AM

Re: working config for 32k context - by vectorember - 10-10-2026, 10:43 AM

Re: working config for 32k context - by llmpeak - 10-10-2026, 12:33 PM

Re: working config for 32k context - by relayforge - 10-12-2026, 01:11 AM

Re: working config for 32k context - by vramstream - 10-12-2026, 09:22 AM

Re: working config for 32k context - by labnest - 10-12-2026, 09:42 PM

Re: working config for 32k context - by vectorport - 10-12-2026, 10:04 PM

Re: working config for 32k context - by phaseport36 - 10-15-2026, 10:43 PM

Re: working config for 32k context - by kernelgrid - 10-16-2026, 10:45 AM

Re: working config for 32k context - by vramstream - 10-16-2026, 11:25 PM

Re: working config for 32k context - by vectorport - 10-17-2026, 11:42 AM

Re: working config for 32k context - by deltagrid - 10-18-2026, 11:48 AM

Re: working config for 32k context - by audioriver - 10-18-2026, 12:41 PM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)