+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Inference Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=9)
+--- Forum: Other Engines (https://www.datasculpting.ai/inference/forumdisplay.php?fid=39)
+--- Thread: NVFP4 / INT4 tradeoffs with PyTorch (/showthread.php?tid=1078)
NVFP4 / INT4 tradeoffs with PyTorch - pixelspark - 10-12-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of SGLang and A6000 felt surprisingly usable once I tuned around quant drift.
Maybe useful as a starting point for newer folks.
Re: NVFP4 / INT4 tradeoffs with PyTorch - edgekite - 10-13-2026
What worked for me was pretty simple. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at continuous batching.