"found point XXX not on grid" with llama-quant on IQ1_S/IQ2_XXS/etc when using imatrix
#1
by
sokann
- opened
Last I tried, I ran into the issue described in https://github.com/ggml-org/llama.cpp/issues/14798. Keen to know what you did to get it to work. Thanks 😄
We get these, too, quite often. I guess we were probably just lucky with our training data for this model, or had a lucky version of llama.cpp at the time. @nicboss do you remember us doing anything special to avoid that?