Inference › RAG & Knowledge Systems › Embeddings v
Embeddings discussion

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Embeddings discussion
vectorshed43 Offline
Member
***
Posts: 72
Threads: 7
Joined: Sep 2026
Reputation: 0
#1
10-06-2026, 08:58 PM
Did a bit of testing and thought I'd post the result here.

I tried this with Phi using PyTorch on 5090. The headline result was better than I expected, but batch size still ended up being the limiting factor.

Curious if anyone else landed in the same place.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.
Find
Reply


Messages In This Thread
Embeddings discussion - by vectorshed43 - 10-06-2026, 08:58 PM
Re: Embeddings discussion - by paperport64 - 10-07-2026, 09:40 AM
Re: Embeddings discussion - by edgecoast - 10-08-2026, 09:53 PM
Re: Embeddings discussion - by vectorshed43 - 10-08-2026, 10:47 PM
Re: Embeddings discussion - by mangoquill - 10-09-2026, 11:22 AM
Re: Embeddings discussion - by edgecoast - 10-11-2026, 03:18 PM
Re: Embeddings discussion - by ggufwire22 - 10-09-2026, 12:13 PM
Re: Embeddings discussion - by vectorshed43 - 10-10-2026, 12:40 PM
Re: Embeddings discussion - by quantnest - 10-10-2026, 08:58 PM
Re: Embeddings discussion - by vectorshed43 - 10-10-2026, 10:19 PM
Re: Embeddings discussion - by rasterhall - 10-11-2026, 12:57 AM
Re: Embeddings discussion - by ggufwire22 - 10-11-2026, 01:38 PM
Re: Embeddings discussion - by vramscope - 10-14-2026, 03:38 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)