+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Drivers / Frameworks / Toolkits (https://www.datasculpting.ai/inference/forumdisplay.php?fid=8)
+--- Forum: PyTorch / JAX / Other Frameworks (https://www.datasculpting.ai/inference/forumdisplay.php?fid=34)
+--- Thread: PyTorch compile got faster? with vLLM (/showthread.php?tid=174)
Pages:
1
2
Re: PyTorch compile got faster? with vLLM - audiopath66 - 09-10-2026
I'd approach it in a boring order. On M3 Max, 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.
Re: PyTorch compile got faster? with vLLM - vramghost - 09-10-2026
Quote:I'd approach it in a boring order. On M3 Max, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot
I'd start with the simpler stack.
Re: PyTorch compile got faster? with vLLM - minthall - 09-10-2026
That matches what I was seeing. That matches what I saw on B200.