Inference › RAG & Knowledge Systems › RAG v
hybrid retrieval results

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
hybrid retrieval results
sparrowbrook Offline
Junior Member
**
Posts: 15
Threads: 3
Joined: Sep 2026
Reputation: 0
#1
10-07-2026, 05:42 PM
Thought I'd post a small recipe because a lot of threads ask similar things.

This isn't revolutionary, but the combination of MLX and Threadripper box felt surprisingly usable once I tuned around batch size.

Maybe useful as a starting point for newer folks.

I care more about stability than squeezing the last possible tokens/sec out of it.
Find
Reply


Messages In This Thread
hybrid retrieval results - by sparrowbrook - 10-07-2026, 05:42 PM
Re: hybrid retrieval results - by turbogrid11 - 10-07-2026, 06:50 PM
Re: hybrid retrieval results - by homelabhenry - 10-09-2026, 07:30 AM
Re: hybrid retrieval results - by kernelghost - 10-09-2026, 08:08 PM
Re: hybrid retrieval results - by llmtrack - 10-11-2026, 08:12 AM
Re: hybrid retrieval results - by sanepeak48 - 10-12-2026, 10:13 PM
Re: hybrid retrieval results - by nanogarden - 10-12-2026, 08:35 AM
Re: hybrid retrieval results - by bytelab - 10-12-2026, 05:04 PM
Re: hybrid retrieval results - by homelabhenry - 10-12-2026, 05:56 PM
Re: hybrid retrieval results - by tinycontext - 10-12-2026, 10:29 PM
Re: hybrid retrieval results - by orbitgarden - 10-14-2026, 11:12 AM
Re: hybrid retrieval results - by cozykite - 10-14-2026, 11:58 AM
Re: hybrid retrieval results - by labpath - 10-14-2026, 01:22 PM
Re: hybrid retrieval results - by sanepeak48 - 10-14-2026, 02:26 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)