prefix caching on repeated workflows with TensorRT-LLM

Thread Rating:

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

Linear Mode

prefix caching on repeated workflows with TensorRT-LLM

turboscope Offline

Offline

Junior Member

Posts: 35
Threads: 8
Joined: Aug 2026
Reputation: 0

#12

10-19-2026, 05:57 AM

Quote:What exact setup are you running? Is this local-only or are you routing anything externally?

I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher. The main thing that moved was latency, not quality.

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-19-2026, 04:56 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-19-2026, 02:07 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-18-2026, 09:59 PM

Re: prefix caching on repeated workflows with TensorRT-LLM - by turbogrid11 - 10-19-2026, 02:19 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by sparrowhall - 10-19-2026, 04:45 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-19-2026, 03:20 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by amberplane - 10-19-2026, 05:18 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by kernelghost - 10-19-2026, 03:26 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-19-2026, 03:51 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by kernelghost - 10-19-2026, 03:58 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by cacheline - 10-19-2026, 04:59 AM

Re: prefix caching on repeated workflows with TensorRT-LLM - by turboscope - 10-19-2026, 05:57 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)