|
NVIDIA driver regression
|
10-09-2026, 06:15 AM
Quote:That matches what I was seeing. The pattern around token cost has been pretty similar for me. The biggest change for me was simplifying the stack inst I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Could be a workload difference, but I wouldn't generalize too fast from one setup.
Mostly CUDA, sometimes wrong, usually measured
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
NVIDIA driver regression - by edgecoast - 10-05-2026, 05:29 PM
Re: NVIDIA driver regression - by latentgarden - 10-07-2026, 05:43 PM
Re: NVIDIA driver regression - by kernelmike - 10-09-2026, 06:15 AM
Re: NVIDIA driver regression - by mintforge - 10-09-2026, 06:29 AM
Re: NVIDIA driver regression - by thetapath - 10-09-2026, 10:41 AM
Re: NVIDIA driver regression - by sparrowkite53 - 10-10-2026, 11:10 AM
Re: NVIDIA driver regression - by dockember - 10-10-2026, 10:56 AM
Re: NVIDIA driver regression - by edgecoast - 10-10-2026, 01:55 PM
Re: NVIDIA driver regression - by emberrunner - 10-10-2026, 06:22 PM
Re: NVIDIA driver regression - by latentgarden - 10-11-2026, 06:37 AM
|
