Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Help with Vector Databases for DeepSeek
#1
Curious what people here are seeing.

I'm mostly working with DeepSeek in MLX on GB200. The part I'm trying to understand is prefix caching.

If you've tested something similar, what did you keep and what did you stop bothering with?

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.
Reply


Messages In This Thread
Help with Vector Databases for DeepSeek - by macronest - 10-13-2026, 02:36 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)