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

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
serving on Blackwell for Phi
sysstation69 Offline
Junior Member
**
Posts: 32
Threads: 1
Joined: Sep 2026
Reputation: 0
#3
10-16-2026, 02:45 PM
What worked for me was pretty simple. Before rebuilding anything, I'd test one clean baseline with Qwen and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Find
Reply


Messages In This Thread
serving on Blackwell for Phi - by pixelcrate82 - 10-16-2026, 05:35 AM
Re: serving on Blackwell for Phi - by macrotinker - 10-16-2026, 02:08 PM
Re: serving on Blackwell for Phi - by sysstation69 - 10-16-2026, 02:45 PM
Re: serving on Blackwell for Phi - by kernelpeak - 10-18-2026, 04:42 PM
Re: serving on Blackwell for Phi - by rasterbench - 10-19-2026, 01:32 AM
Re: serving on Blackwell for Phi - by kernelgrid - 10-18-2026, 06:43 PM
Re: serving on Blackwell for Phi - by routecrate - 10-18-2026, 09:04 PM
Re: serving on Blackwell for Phi - by rocmmixer - 10-18-2026, 09:13 PM
Re: serving on Blackwell for Phi - by quiethouse - 10-19-2026, 02:21 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)