what are you all running this week

[rasterpoint]

This keeps coming up in conversation so I figured I'd start a thread.

It feels like the conversation has shifted hard toward inference and serving details lately, and honestly that makes sense once you start dealing with HBM constraints.

Curious whether that lines up with what other people are seeing.

For context, I'm not chasing leaderboard numbers. I mostly want the system to feel consistent day to day.

[mangofield33]

What exact setup are you running? Are you testing this on GB200 or something else?

[southpatch]

Appreciate the detail. The pattern around tool calling has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[cacheplane98]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mistral and compare from there.

[vectorfield]

A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[vramarch]

Appreciate the detail. I ended up in about the same place using PyTorch. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable. At this point the real bottleneck is my patience.

[rocmrunner40]

A couple things I'd check first. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of

What worked for me was pretty simple. 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.

[quiettoken]

Good point. The pattern around long context has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

[plaingarden18]

That matches what I was seeing. That matches what I saw on M3 Max.

[marbletrack]

A couple things I'd check first. On 5090, the easiest win is often to back off the aggressive settings and see whether the problem survives. Once you know the plain path works, then add the faster path back in piece by piece.