sandboxing agent actions

[flintriver50]

Posting this in case it saves someone else a little time.

I'm helping a small team set up a local workflow. We don't need a giant stack, but we do care about token cost.

Would rather learn from your scars than collect my own all at once.

[cacheline]

worth checking the driver first.

[mintquill]

I tested this tonight. On dual 3090 with MLX, I saw basically the same behavior. The surprise was that memory pressure showed up before throughput collapsed.

[stackpilot]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost. Once you know the plain path works, then add the faster path back in piece by piece.

[cudacrate]

What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost. Once you

I'd approach it in a boring order. On 7900 XTX, the easiest win is often to back off the aggressive settings and see whether the problem survives. Not glamorous advice, but repeatable baselines save a lot of time.

[turboscope5]

[quote]What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at token cost. On

I don't think that's the whole story. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.