Inference › Harnesses, Agents & Orchestration › Workflows / Automation v
DeepSeek V4.1 impressions with PyTorch

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
DeepSeek V4.1 impressions with PyTorch
routecraft Offline
Member
***
Posts: 193
Threads: 27
Joined: Aug 2026
Reputation: 0
#11
10-04-2026, 11:44 AM
That matches what I was seeing. The pattern around prefill/decode split has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
routing beats arguing over one perfect model
Find
Reply


Messages In This Thread
Re: DeepSeek V4.1 impressions with PyTorch - by routecraft - 10-04-2026, 11:44 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)