RAG chunking that actually helped with TensorRT-LLM

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

RAG chunking that actually helped with TensorRT-LLM

localtinker Offline

Junior Member

Posts: 37
Threads: 2
Joined: Aug 2026
Reputation: 0

#13

10-17-2026, 08:19 AM

That matches what I was seeing. I ended up in about the same place using vLLM. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

small models can still be good

Find

« Next Oldest | Next Newest »

Messages In This Thread

RAG chunking that actually helped with TensorRT-LLM - by relaysupply90 - 10-11-2026, 02:49 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by mangotinker73 - 10-12-2026, 03:24 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by northgarden37 - 10-12-2026, 07:44 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by labline - 10-13-2026, 08:51 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by mangowire - 10-13-2026, 08:34 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by thetarunner - 10-14-2026, 09:12 AM

Re: RAG chunking that actually helped with TensorRT-LLM - by oxidestream - 10-14-2026, 01:21 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by rocmriley - 10-16-2026, 01:42 AM

Re: RAG chunking that actually helped with TensorRT-LLM - by routecraft - 10-16-2026, 02:36 AM

Re: RAG chunking that actually helped with TensorRT-LLM - by llmarch51 - 10-16-2026, 11:02 AM

Re: RAG chunking that actually helped with TensorRT-LLM - by thetagrid15 - 10-16-2026, 03:27 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by rocmcrate26 - 10-16-2026, 11:38 PM

Re: RAG chunking that actually helped with TensorRT-LLM - by localtinker - 10-17-2026, 08:19 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)

Login
Username:
Password:	Lost Password?
	Remember me

Sign in with X.com