Inference › RAG & Knowledge Systems › Embeddings v
Embeddings discussion

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
Embeddings discussion
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#13
10-01-2026, 04:40 AM
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at tail latency. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
Embeddings discussion - by quantnest - 09-23-2026, 06:25 PM
Re: Embeddings discussion - by ggufwire22 - 09-23-2026, 06:58 PM
Re: Embeddings discussion - by vramscope - 09-23-2026, 09:36 PM
Re: Embeddings discussion - by edgecoast - 09-23-2026, 09:56 PM
Re: Embeddings discussion - by vectorshed43 - 09-23-2026, 10:51 PM
Re: Embeddings discussion - by paperport64 - 09-24-2026, 01:31 AM
Re: Embeddings discussion - by vramscope - 09-25-2026, 01:48 PM
Re: Embeddings discussion - by torchdesk - 09-25-2026, 01:57 PM
Re: Embeddings discussion - by quantnest - 09-25-2026, 02:35 PM
Re: Embeddings discussion - by ggufwire22 - 09-25-2026, 03:21 PM
Re: Embeddings discussion - by oxidestream - 09-28-2026, 03:38 PM
Re: Embeddings discussion - by kernelarch - 09-29-2026, 03:56 PM
Re: Embeddings discussion - by cacheline - 10-01-2026, 04:40 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)