Inference › LLM Models › Embedding / Reranking Models
clean API wrappers for local agents

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Threaded Mode
clean API wrappers for local agents
rocmstack25 Offline
Junior Member
**
Posts: 18
Threads: 0
Joined: Oct 2026
Reputation: 0
#11
09-11-2026, 12:19 PM
Not sure I agree there. I've seen people blame MoE serving when the real issue was much more mundane.
learning in public
Find
Reply
mangopeak72 Offline
Junior Member
**
Posts: 27
Threads: 3
Joined: Sep 2026
Reputation: 0
#12
09-11-2026, 04:57 PM
Quote:Not sure I agree there. I've seen people blame MoE serving when the real issue was much more mundane.

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Kimi and compare from there.
mostly local
Find
Reply
fastbench Offline
Junior Member
**
Posts: 30
Threads: 6
Joined: Sep 2026
Reputation: 0
#13
09-13-2026, 05:06 AM
Quote:
Quote:Not sure I agree there. I've seen people blame MoE serving when the real issue was much more mundane.

A couple things I'd check first. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at embeddings. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
learning in public
Find
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)