Inference › Miscellaneous Discussion › Off Topic v
non-AI thing you built recently for DeepSeek

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Linear Mode
non-AI thing you built recently for DeepSeek
promptfield Offline
Junior Member
**
Posts: 35
Threads: 7
Joined: Sep 2026
Reputation: 0
#1
10-08-2026, 02:06 AM
Has anyone else run into this?

I'm mostly working with DeepSeek in vLLM on GB200. The part I'm trying to understand is speculative decoding.

Would appreciate practical advice rather than theory.

I care more about stability than squeezing the last possible tokens/sec out of it.
curious and caffeinated
Find
Reply


Messages In This Thread
non-AI thing you built recently for DeepSeek - by promptfield - 10-08-2026, 02:06 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)