10-19-2026, 12:04 AM
Did a small comparison this afternoon. I couldn't reproduce the slowdown until I pushed context much higher.
|
prefill bottlenecks on longer prompts on A6000
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
prefill bottlenecks on longer prompts on A6000 - by homelabhenry - 10-19-2026, 03:51 AM
Re: prefill bottlenecks on longer prompts on A6000 - by vrambandit - 10-18-2026, 11:41 PM
Re: prefill bottlenecks on longer prompts on A6000 - by deltastation - 10-19-2026, 12:04 AM
Re: prefill bottlenecks on longer prompts on A6000 - by labline - 10-18-2026, 09:23 PM
Re: prefill bottlenecks on longer prompts on A6000 - by rocmstack25 - 10-19-2026, 12:36 AM
Re: prefill bottlenecks on longer prompts on A6000 - by quiettoken - 10-19-2026, 05:23 AM
|