Inference › Inference Engines › TensorRT-LLM v
quant support gaps

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
quant support gaps
batchscope72 Offline
Junior Member
**
Posts: 39
Threads: 8
Joined: Aug 2026
Reputation: 0
#8
10-11-2026, 05:41 AM
Quote:
Quote:I tested this tonight. I couldn't reproduce the slowdown until I pushed context much higher.

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there.
mostly local
Find
Reply


Messages In This Thread
quant support gaps - by sysstation69 - 10-09-2026, 05:24 AM
Re: quant support gaps - by routeforge64 - 10-09-2026, 06:12 AM
Re: quant support gaps - by batchcraft - 10-10-2026, 11:06 PM
Re: quant support gaps - by kernelgrid - 10-09-2026, 10:33 AM
Re: quant support gaps - by torchtrack24 - 10-13-2026, 07:41 AM
Re: quant support gaps - by routecrate - 10-11-2026, 12:04 AM
Re: quant support gaps - by torchtrack24 - 10-11-2026, 12:29 AM
Re: quant support gaps - by rocmriley - 10-11-2026, 01:24 AM
Re: quant support gaps - by batchscope72 - 10-11-2026, 05:41 AM
Re: quant support gaps - by sysstation69 - 10-11-2026, 06:14 PM
Re: quant support gaps - by ggufvault - 10-13-2026, 06:58 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)