prefill bottlenecks on longer prompts

Thread Rating:

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

Linear Mode

prefill bottlenecks on longer prompts

quiettoken Offline

Offline

Member

Posts: 142
Threads: 20
Joined: Sep 2026
Reputation: 0

#12

10-19-2026, 01:43 AM

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

small models can still be useful

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

prefill bottlenecks on longer prompts - by mellowsupply - 10-18-2026, 01:01 AM

Re: prefill bottlenecks on longer prompts - by quietarch - 10-18-2026, 02:14 AM

Re: prefill bottlenecks on longer prompts - by quiettoken - 10-19-2026, 01:43 AM

Re: prefill bottlenecks on longer prompts - by deltapoint17 - 10-18-2026, 05:19 PM

Re: prefill bottlenecks on longer prompts - by tinycontext - 10-18-2026, 05:46 PM

Re: prefill bottlenecks on longer prompts - by oxidemixer - 10-18-2026, 05:56 PM

Re: prefill bottlenecks on longer prompts - by amberpatch25 - 10-18-2026, 06:28 PM

Re: prefill bottlenecks on longer prompts - by sanepeak48 - 10-18-2026, 07:27 PM

Re: prefill bottlenecks on longer prompts - by kernelghost - 10-18-2026, 09:14 PM

Re: prefill bottlenecks on longer prompts - by pixelspark - 10-19-2026, 12:00 AM

Re: prefill bottlenecks on longer prompts - by audiopoint18 - 10-19-2026, 12:26 AM

Re: prefill bottlenecks on longer prompts - by byteyard - 10-19-2026, 01:05 AM

Re: prefill bottlenecks on longer prompts - by visionforge - 10-19-2026, 02:28 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)