Inference › Training & Customization › Distillation v
RAG recall vs speed tradeoff for Phi

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
RAG recall vs speed tradeoff for Phi
vrampilot Offline
Junior Member
**
Posts: 28
Threads: 3
Joined: Aug 2026
Reputation: 0
#11
10-07-2026, 06:36 AM
Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not quality.
Find
Reply
tensorkite Offline
Member
***
Posts: 53
Threads: 4
Joined: Sep 2026
Reputation: 0
#12
10-07-2026, 08:56 AM
Did a small comparison this afternoon. On 4090 with SGLang, I saw basically the same behavior.
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)