Ed Addario

**Really** looking forward to this PR being merged into master! In the meantime, you may already know this but passing along a tip shared by @David-AU-github in [here](https://github.com/ggml-org/llama.cpp/pull/12718#issuecomment-2889528626) that has...

Echoing @nicoboss' sentiment. This is a very nice enhancement @compilade. Thank you. I've been testing by running different permutations of options, including roundtrips on each test, and comparing the resulting...

Assuming no additional changes on this PR, the enhanced version of #12718 is ready to go as soon as this one is merged

PR #12511 changed the llama_model_quantize_params API by introducing an additional void * tensor_types parameter

Haven't had much of an opportunity to play with T2I models yet but if someone can point me to a sample model and imatrix file, happy to make the necessary...

Apologies for shotgun approach @ggerganov / @slaren / @ngxson, I'm not sure what the proper process to request a review is. This PR addresses #12511 deficiencies. Happy to close or...

Thank you @ngxson. Yes, it will process any imatrix file produced by llama-imatrix, but it is restricted to single file (does not deal with multiple --in-file)

Not sure if I'm understanding the comment correctly @jukofyork, but the logic I'm using to identify the most influential tensors/layers is to simply average the importance scores (IS) for each,...

Very clear now, thanks @compilade. You're correct, I'm using the mean squared activation averaged to identify which tensors/layers produce large magnitude activations and ~~whilst~~ agree it isn't as accurate as,...

Had a chance to think this more thoroughly and now get the implications of @jukofyork and @compilade's comments. Agree my current approach is not really identifying influence but rather score...