Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
prefill bottlenecks on longer prompts on A6000
#1
Thought I'd post a small recipe because a lot of threads ask similar things.

Just sharing a setup that ended up working reasonably well: Gemma, MLX, 4090, with a lot of attention on MoE serving.

If someone wants the exact settings I can clean them up and post them.
mostly local
Reply


Messages In This Thread
prefill bottlenecks on longer prompts on A6000 - by batchscope72 - 10-08-2026, 08:26 PM

Forum Jump:


Users browsing this thread: 1 Guest(s)