best sandbox for trying risky tools: anyone testing this?

[cacheworks]

Did a bit of testing and thought I'd post the result here.

I tried this with Mistral using MLX on M3 Max. The headline result was better than I expected, but continuous batching still ended up being the limiting factor.

Curious if anyone else landed in the same place.

My use case is pretty ordinary: local chat, some document work, and occasional batch jobs.

[benchplease]

Need a little more detail here. Do you see the same thing with a smaller batch or shorter prompt?

[thetafield]

Maybe, but I had the opposite result. I've seen people blame NVFP4 when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.

[kernelmike]

Maybe, but I had the opposite result. I've seen people blame NVFP4 when the real issue was much more mundane. Worth testing the simpler explanation be

I hit almost the same issue last night.

[vramarch]

I don't think that's the whole story. I've seen people blame tool calling when the real issue was much more mundane. Worth testing the simpler explanation before adopting the more interesting one.

[audiodesk]

I don't think that's the whole story. I've seen people blame tool calling when the real issue was much more mundane. Worth testing the simpler explana

Interesting, I hadn't tried that. That matches what I saw on Threadripper box. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

If you post your exact settings, people here can probably narrow it down pretty fast.

[rasterhall]

Not sure I agree there. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[cozykite]

I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. Once you know the plain path works, then add the faster path back in piece by piece.

[plainline]

What worked for me was pretty simple. If you're on SGLang, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[batchshed]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?