new here, what's your stack: early impressions

[cacheplane98]

Interesting, I hadn't tried that. I ended up in about the same place using SGLang.

[quiettoken]

I'd approach it in a boring order. If you're on PyTorch, 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.

[quiettoken]

Appreciate the detail. I don't think your conclusion is far off. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[promptpoint]

Tried to reproduce it just now. I couldn't reproduce the slowdown until I pushed context much higher. I expected the model choice to matter more than it did.

[vectorshed43]

I think the bottleneck is somewhere else. I've seen people blame INT4 when the real issue was much more mundane. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[cacheplane98]

I'd start with the simpler stack.