Multimodal discussion

[cudaworks]

I think the bottleneck is somewhere else. I've seen people blame quant drift when the real issue was much more mundane. Could be a workload difference, but I wouldn't generalize too fast from one setup.

[macropilot]

Did a small comparison this afternoon. On A6000 with MLX, I saw basically the same behavior.

[torchshed66]

Did a small comparison this afternoon. On A6000 with MLX, I saw basically the same behavior.

What exact setup are you running? Do you see the same thing with a smaller batch or shorter prompt?

[batchember]

same here on my side.

[visionforge]

I'd approach it in a boring order. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.