Inference › Inference Engines › TensorRT-LLM v
serving on Blackwell for FLUX

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
serving on Blackwell for FLUX
cacheline Offline
Senior Member
****
Posts: 341
Threads: 51
Joined: Sep 2026
Reputation: 0
#8
09-02-2026, 09:52 PM
I don't think that's the whole story. I've seen people blame long context when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.
measure twice, benchmark three times
Find
Reply


Messages In This Thread
serving on Blackwell for FLUX - by kernelmike - 08-31-2026, 10:04 AM
Re: serving on Blackwell for FLUX - by audioforge - 08-31-2026, 06:52 PM
Re: serving on Blackwell for FLUX - by kernelmike - 08-31-2026, 11:54 PM
Re: serving on Blackwell for FLUX - by vectorport - 09-01-2026, 04:37 AM
Re: serving on Blackwell for FLUX - by edgecoast - 09-02-2026, 05:15 PM
Re: serving on Blackwell for FLUX - by vramstream - 09-04-2026, 07:54 PM
Re: serving on Blackwell for FLUX - by cacheline - 09-02-2026, 09:52 PM
Re: serving on Blackwell for FLUX - by vectorport - 09-05-2026, 08:14 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)