Inference › RAG & Knowledge Systems › Vector Databases
Vector Databases discussion for DeepSeek

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Vector Databases discussion for DeepSeek
tinycontext Offline
Member
***
Posts: 112
Threads: 12
Joined: Sep 2026
Reputation: 0
#3
10-02-2026, 10:29 AM
Quote:worth checking the driver first.

I tested this tonight. On Threadripper box with TensorRT-LLM, I saw basically the same behavior. The main thing that moved was latency, not quality.
context windows are not a product strategy
Find
Reply


Messages In This Thread
Re: Vector Databases discussion for DeepSeek - by tinycontext - 10-02-2026, 10:29 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)