|
RAG chunking that actually helped: worth it?
|
09-28-2026, 07:22 AM
Quote:A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at MoE serving. Not glamorous I think the bottleneck is somewhere else. I've seen people blame workstation thermals when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
still benchmarking everything
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
RAG chunking that actually helped: worth it? - by dockbrook21 - 09-28-2026, 12:18 AM
Re: RAG chunking that actually helped: worth it? - by fastfield4 - 09-28-2026, 05:09 AM
Re: RAG chunking that actually helped: worth it? - by localpatch - 09-28-2026, 07:22 AM
Re: RAG chunking that actually helped: worth it? - by bytesupply76 - 09-28-2026, 08:48 PM
Re: RAG chunking that actually helped: worth it? - by audioforge - 09-28-2026, 07:35 AM
Re: RAG chunking that actually helped: worth it? - by quietcraft - 09-28-2026, 08:11 PM
Re: RAG chunking that actually helped: worth it? - by mintstation99 - 09-28-2026, 09:42 PM
Re: RAG chunking that actually helped: worth it? - by localpatch - 09-28-2026, 11:20 PM
Re: RAG chunking that actually helped: worth it? - by llmtrack - 09-30-2026, 11:56 AM
Re: RAG chunking that actually helped: worth it? - by macrostack69 - 09-30-2026, 01:00 PM
Re: RAG chunking that actually helped: worth it? - by lablab - 09-30-2026, 03:39 PM
|
